CHAPTER – 1

1.1 INTRODUCTION

"Your career is like a garden. It can hold an assortment of life's energy that yields a bounty for you.
You do not need to grow just one thing in your garden. You do not need to do just one thing in your
career."
—Jennifer Ritchie Payette

The word “guidance” originated back in the 1530s, and is defined as the process of directing
conduct. Career guidance can be defined as a comprehensive, developmental program designed to
assist individuals in making and implementing informed educational and occupational choices. In
simple words, it is a journey on which people develop to make mature and informed decisions. It is
the act of guiding or showing the way; it is the act of seeking advice.

Career guidance is the guidance given to individuals to help them acquire the knowledge,
information, skills, and experience necessary to identify career options, and narrow them down to
make one career decision. This career decision then results in their social, financial and emotional
well-being throughout.

In an age where career queries are not uncommon, it’s important to answer queries related to career
guidance or career, in general. Employing artificial intelligence powered tools for career
development is a newly developed technique of assisting people in picking the right career. From
now let’s make it simple; visualize a clever advisor taking note of the things you like or your
aspirations and suggesting suitable career paths. Instead of working in seeking vague information
alone, without utilizing first-hand knowledge, artificial intelligence sifts through thousands of data
such as trends in the market or
industries, average salaries, and even individuals’ likes. If one is good at resolving issues but enjoys
doing creative work, for instance, designing, AI could advocate for design related employment. This
style allows you to consider many factors, reduces the time taken to search for career paths, and
exposes you to a new range of options during the career search campaign process, making it much
more straightforward and customized to fit your needs.

1
AI-enhanced career guidance is a modern way of helping people choose the right job path using
artificial intelligence. Imagine having a smart advisor that listens to your interests, skills, and goals,
and then suggests career options that might be a great fit. Instead of just relying on general advice,
AI looks at vast amounts of data, such as industry trends, salary expectations, and personal
preferences, to offer personalized recommendations. For example, if you’re good at problem
solving but enjoy creative tasks, AI might suggest careers in design or tech. This approach helps
you make informed decisions, saves time, and opens up new possibilities, making the career
exploration process clearer and more tailored to you.

Career decision-making represents a critical juncture in an individual's life, significantly impacting

long-term professional achievement and personal fulfillment. Traditional methods of career
guidance typically encompass self-assessments, consultations with career counselors, and the use of
standardized testing; however, these approaches may not consistently yield the most pertinent or
individualized career recommendations. The emergence of artificial intelligence (AI) and big data
has revolutionized career guidance systems, enabling them to provide tailored, scalable, and real-
time career advice.

By leveraging extensive datasets that encompass job market trends, skill requirements, and
individual competencies, AI can effectively direct users toward optimal career trajectories.
This paper introduces an AI-enhanced career guidance model that includes the following
components:
1. User Profiling – Analyzing individual strengths, preferences, and aspirations.
2. AI-Driven Career Matching – Employing machine learning (ML) and natural language
processing (NLP) to generate personalized career recommendations.
3. Labor Market Analytics – Incorporating real-time analyses of job demand.
4. Skill Assessment and Gap Analysis – Offering recommendations for skill enhancement based
on market requirements.

The objective of this study is to bridge the divide between education and employment by rendering
career guidance more data-informed, adaptive, and prepared for future challenges.

1.2 Working of the System

AI-Enhanced career guidance works in following manner -:

2
 Fig. 1 shows the working of the system.
The system works in below mentioned way -:
1. Start: Home Page
o This is where users land on the platform. It should provide a welcoming interface
with options to either Register or Login.
2.Registration / Login
o Registration: If the user is new to the platform, they create an account by entering
their basic details (name, email, etc.).
o Login: If the user has already registered, they can simply log in.

3. Dashboard (Login Success)

o Once the user logs in, they are redirected to their personalized dashboard. This page
displays relevant career insights, progress, and options to start their career planning
process.
4. Self-Assessment (Rate Yourself)

o Rate Yourself: The user assesses their skills, interests, values, and work preferences.
This could be done through a self-assessment tool that scores and profiles the user.

o Aptitude & Competency Test: The user takes a more detailed test (e.g., personality
assessment, skills inventory, or IQ test) to evaluate their professional strengths and
areas for growth.

3
 5. Career Guidance (AI-Driven)

o Discover Your Career Paths: Based on the user’s assessment results, the system
suggests personalized career paths or options that align with their skills and
preferences.

o Suggested Career Paths: The AI provides a list of recommended career roles and
industries based on the user’s aptitudes and interests.

6. Job Role Exploration

o Check Suitable Job Roles: The system shows a curated list of job titles that fit the
user’s profile. This section includes detailed job descriptions, key responsibilities,
and required skills.
o Understand Your Job Roles: A deeper dive into the responsibilities, skills, career
growth potential, and job requirements for each suggested job role.
7. Skill Development
o Courses Based on Latest Skillset Requirements: Based on the job roles identified
earlier, the system suggests specific courses or certifications required to meet the
latest industry demands.
8. Networking (Knowledge Network Path)
o Knowledge Network Path: The user can access a network of professionals,
mentors, or industry-specific communities that help them expand their
career opportunities. This could be through online networking events,
discussion forums, or career development groups.

1.3 Scope of AI-Enhanced career guidance -:

The scope of AI-enhanced career guidance is broad and offers many benefits. Here are some key
points:
1. Personalized Career Recommendations: AI helps suggest jobs based on your skills, interests,
and personality, rather than just general advice.
2. Skills Gap Analysis: It identifies what skills you need to improve or learn for specific careers,
helping you stay competitive.
3. Industry Trends: AI tracks changes in the job market and shows which industries are growing,
guiding you toward high-demand fields.

4
4. Learning Pathways: AI recommends courses or training programs to help you gain the skills
needed for your desired job.
5. Salary Insights: It provides salary expectations for different careers, helping you make better
financial decisions.
6. Job Matching: AI helps match your profile with suitable job openings, making the job search
more efficient.
7. Career Growth Insights: AI predicts potential career advancement paths based on your
experience and skills.
8. Access to Global Opportunities: AI can help you explore careers not limited by location,
opening doors to international opportunities.

1.4 Methodology-:

1.4.1 Information Gathering and Evaluation:

It is founded on a thorough examination of the body of research, case studies, and practical uses of
AI in career counseling. Academic journals, industry reports, and publicly accessible datasets about
AI-powered career counseling platforms are some examples of data sources. Interviews with
professionals in the domains of AI, education, and career counseling are also incorporated into the
review.

1.4.2 AI Technologies in Career Guidance:

In the context of career counseling, the following AI technologies are investigated:

1.ML, or machine learning: Large datasets are analyzed, patterns are found, and career
outcomes are predicted based on individual profiles using machine learning algorithms. To
generate tailored suggestions, these algorithms can be trained using historical data.

2. Natural Language Processing (NLP): NLP makes it possible for AI systems to

comprehend and interpret human language, which makes career counseling platforms more
engaging and easy to use. In order to offer customized guidance, NLP can also be used to
evaluate job descriptions, resumes, and other text-based data.

5
 3. Data Analytics: Real-time labor market data can be processed by AI-driven data
analytics to spot trends, skill shortages, and new employment opportunities. Current career
recommendations can be made using this information.

4. Recommender Systems: Based on user preferences and past data, recommender systems
in career counseling can make recommendations for educational programs, career paths, and
employment opportunities, much like those found in e-commerce and entertainment.

1.4.3 Evaluation Metrics:

The following metrics are taken into consideration when evaluating the efficacy of AI-enhanced
career guidance systems:

1. Recommendation Accuracy: The extent to which AI-generated career suggestions correspond

with personal objectives, aptitudes, and industry needs.

2. User Satisfaction: Based on surveys and feedback, this is the degree of satisfaction that users of
AI-powered career counseling platforms report.

3. Accessibility: The degree to which people from various socioeconomic and geographic
backgrounds can use AI-enhanced career counseling systems.

4. Bias and Fairness: The extent to which AI systems reduce bias and encourage fair career
recommendations for all users, irrespective of socioeconomic status, gender, or race.

5. Real-Time Adaptability: AI systems' capacity to adjust to shifting labor market conditions and
deliver pertinent career guidance in real time.

6
1.5 Related Work -:

Artificial Intelligence (AI) has profoundly transformed the landscape of career guidance by
providing tailored, data driven recommendations that enhance the decision-making process. This
section reviews existing literature that underscores the significance of AI in various aspects of
career planning, including cloud-based career matching, learning analytics, and the applications of
generative AI.

A. Development of Career Guidance Technologies

Historically, career counseling was predominantly based on static assessments, in-person advisory
sessions, and manual job-matching algorithms. These traditional methods were limited in scalability
and struggled to keep pace with the rapid changes in the labor market. The advent of computer
assisted career guidance (CACG) systems marked the initial phase of automated career assessments,
which incorporated early models of data-driven decision-making. With the emergence of AI,
techniques such as machine learning (ML) and natural language processing (NLP) have been
employed to provide real-time, adaptive career recommendations, thereby significantly enhancing
the accuracy and personalization of decision-making processes.

B. AI-Driven Career Counseling

Recent research highlights how AI-powered career guidance systems leverage big data, NLP, and
predictive modeling to personalize career recommendations.

7
 Table 1: Summary of AI-Based Career Guidance Research

These studies confirm that AI-based career guidance outperforms traditional approaches by
providing adaptive, scalable, and data-driven recommendations.
C. Generative AI and Intelligent Career Assistants
Generative artificial intelligence, exemplified by platforms such as ChatGPT, Bard, and Claude, has
significantly transformed the landscape of career planning by providing dynamic insights through
natural language interactions. A prominent illustration of this innovation is the CABIN-NET and
CGC-bot, which employ machine learning (ML) and natural language processing (NLP) to analyze
conversational data and align users' interests with occupations listed in the O*NET database. These
AI-driven career assistants offer several advantages: they enhance accessibility by providing round-
the-clock career guidance, foster engagement through interactive discussions about career options,
and deliver personalized recommendations based on real-time user interactions. Despite the
improvements in user experience facilitated by generative AI, existing research indicates that there

8
is a need for further advancements in ethical decision-making and the mitigation of bias within
these systems.

D. AI-Driven Career Matching and Learning Analytics

Artificial intelligence-based career tools are increasingly incorporating learning analytics (LA) to
monitor user progress and dynamically refine recommendations. Notable developments in this area
include Career Decision-Making Models (CDM), which enable AI to align user interests, learning
trajectories, and job market trends to enhance decision-making processes. Additionally, the
Technology Acceptance Model (TAM) assesses user adoption and the perceived utility of AI-
driven career tools. Furthermore, predictive learning analytics leverage historical student
performance data to estimate the probabilities of career success. These advancements contribute to
ensuring that career recommendations are more data-driven and continuously adaptable to
changing circumstances.

E. Cloud-Based AI Solutions for Career Guidance

Cloud-based artificial intelligence career platforms have emerged as a means to facilitate the career
decision-making process by linking students, parents, educators, and industry stakeholders. These
systems employ real-time labor market analytics to recommend pertinent career options, deliver
personalized assessments of skill gaps to identify competencies that require development, and
provide automated recommendations for learning pathways, incorporating massive open online
courses (MOOCs) such as Coursera and Udemy. By bridging the divide between education and
employment, cloud-based AI solutions ensure that users are equipped with current and relevant
career insights.

F. Ethical Considerations and Challenges in AI Career Guidance

Despite AI’s benefits, several challenges remain in career counseling applications

Challenge Impact Possible Solution

AI Bias & AI may favor certain demographics Implement bias detection algorithms.
Fairness due to biased training
data.

9
Data Privacy Storing sensitive career data raises Use secure,
Issues security concerns. GDPR-compliant AI models.

Interpretability Users may not understand why AI Implement Explainable AI (XAI) models.
recommends
certain careers.
Table 2: Ethical AI research emphasizes the need for transparency, fairness, and privacy in AI-driven career
recommendations.

10
 CHAPTER – 2

2.1 Literature Review

Seyedali Ahrari, et al (2024). The book "Exploring Youth Studies in the Age of AI" delves into
the intricate relationship between Artificial Intelligence (AI) and the youth of Generation AI,
highlighting the dual influence of technological advancement and youthful adaptability in the digital
era. In this paper the chapters are organized around three main themes: digital well-being and
mental health, educational and career development, and socio-demographic diversity and ethical
considerations. Each theme explores how AI influences these areas, offering a holistic view of the
relationship between AI and youth. The book argues for the importance of personalized and
adaptive educational and career guidance, facilitated by AI's capabilities in analyzing large datasets
and tailoring content to individual needs. The book also identifies a gap in comprehensive research
on AI's role in dynamic career planning within vocational education, calling for further studies to
explore how generative AI can enhance career guidance services. Ultimately, the book serves as a
visionary guide, urging readers to engage with the challenges and opportunities of the digital age
and contribute to shaping a future where technology serves the greater good, particularly for the
youngest members of society.

Kehinde Hussein Lawal, et al (2024) The literature review explores the evolving role of AI in
career counseling, highlighting the need for a cloud-based, personalized model due to the dynamic
labor market. Traditional methods are criticized for their outdated practices and limited coverage.
AI offers personalized guidance by analyzing extensive data on market trends and individual
characteristics, enhancing career recommendations. AI-powered platforms can proactively propose
suitable careers, but more research is needed in this area. A collaborative approach involving
students, parents, educational institutions, and industries is emphasized, enhancing communication
and mutual understanding of career paths. The cloud-based model provides wide access,
accommodating more users and meeting the increasing demand for career counseling. Institutions
and industries can benefit by tailoring curricula and identifying future talents. This innovative
model aims to align career choices with individual skills and market demands, ensuring students are
better prepared for the workforce. The prototype was tested with a diverse sample from Nigeria’s
North Central region, demonstrating the model's effectiveness in matching users with suitable

11
career paths and bridging educational and industrial needs. Though positively received, challenges
such as information overload and data reliability emerged, highlighting areas for improvement in
future iterations.

Sarah Bankins, et al (2024) In a rapidly evolving labor market, traditional career counseling
practices often fall short in addressing the unique skills and preferences of individual learners. The
need for a new approach is crucial, and AI offers a promising solution. By leveraging AI, a cloud-
based life decision-making model can be developed, uniting students, parents, educational
institutions, and industries. Conventional career counseling methods, characterized by outdated
diagnostics and broad labor market information, fail to account for the diverse needs and future job
prospects of learners. AI's potential in personalized career guidance comes from its ability to
analyze large datasets, including market trends and individual profiles, to provide tailored career
recommendations. Studies suggest AI-driven platforms can offer more effective career counseling
by incorporating dynamic data on job market demands. A collaborative model involving students,
parents, educators, and employers can enhance career management, allowing each stakeholder to
contribute to a more informed decision-making process. The cloud-based model provides
widespread access, making career counseling more inclusive and adaptable to technological
advancements and increasing demands.

Jingyi Duan, et al (2024) The evolution of career guidance in vocational education has shifted
from generalized, broad-based advisories to more individualized strategies. Historically, career
guidance catered to the average student, often neglecting individual ambitions and capabilities.
Advances in educational psychology and pedagogy have led to the recognition of the need for
personalized career guidance, emphasizing individual assessments, career coaching, and
personalized learning agendas. These approaches align educational and career paths with students'
interests and goals, leading to more effective career preparation. Generative AI, through
technologies like Natural Language Processing (NLP) and Machine Learning (ML) models, has
significantly contributed to this shift. NLP allows systems to understand and generate human
language contextually, while ML models predict and tailor content to users' needs. In education,
these technologies create personalized learning materials, adaptive learning platforms, and
intelligent tutoring systems. AI's ability to analyze large datasets to identify learning patterns and
anticipate educational needs enhances personalized learning experiences. Despite AI's widespread

12
use in education, there is a lack of comprehensive studies on its application for dynamic career
planning in vocational education. This gap highlights the need for further research on how
generative AI can innovate career planning and guidance services to be more personalized,
adaptive,anticipatory.

Gedrimiene et al. (2024) explored the advantages and challenges of using an AI-enhanced
Learning Analytics (LA) tool for career guidance. This study, focusing on users' perspectives,
analyzed the tool's effectiveness through the Technology Acceptance Model (TAM) and Career
Decision-Making (CDM) model. The researchers found that the AI tool provided significant
support in areas like information provision, research and analysis, career diversification, direction in
decision-making, and self-reflection. Users reported that these features were beneficial in
navigating uncertain life transitions and making informed career choices, highlighting the tool's role
in facilitating smoother career transitions and enhancing decision-making confidence. However,
challenges such as usability issues and the need for more personalized options were also noted,
indicating areas for further development.

Nwoke et al. (2019) In their examination of youth migration in Nigeria, highlight how
socioeconomic challenges, such as limited employment, insecurity, and climate change, drive
young Nigerians to seek better opportunities abroad. Migration, particularly among youths aged 18-
35, emerges as a pursuit for quality education, employment, and personal growth, though it often
leads to significant skill drain within Nigeria (Smith et al., 2014). This trend poses a dual impact: on
one hand, it encourages skill acquisition; on the other, it results in the loss of skilled labor needed
for national development. Jyoti (2021) emphasizes the potential benefits of migration for education
and empowerment, yet notes the barriers faced by underfunded migrants. Further analysis by Owo
(2020) suggests that enhancing digital skills and creating remote job opportunities could counteract
youth migration. These scholars argue that digital skills training and remote work possibilities could
foster job creation and reduce the motivation for young people to leave Nigeria, as seen in programs
like Nigeria’s 3MTT and FGN ALAT Skillnovation.

Sathish et al. examine how Artificial Intelligence (AI) is transforming career development through
personalized career guidance and improved job matching, skill alignment, and employee

13
engagement. AI-driven platforms, they note, simplify career exploration by using algorithms to
provide customized career path recommendations that align with individuals' unique skills,
interests, and goals. These platforms enhance recruitment by matching candidate profiles with job
requirements and further support skill development through personalized resources, helping users
close gaps in their career paths. Additionally, the chapter underscores the ethical need for
transparency and fairness in AI-based guidance, advocating for policies that address potential biases
to ensure responsible and equitable AI use in career recommendations.

Mahure et al. (2024) present a robust framework for enhancing career guidance systems, focusing
on a multi-faceted approach that integrates secure user authentication, data collection, academic
evaluation, and advanced skill assessments. Central to this system is a Cognitive Decision Support
module, which utilizes analytical tools to interpret users' cognitive responses, generating tailored
career suggestions. Additionally, a career prediction component powered by algorithmic models,
including XGBoost, forecasts potential career paths and recommends compatible institutions
nationwide. A dynamic skill assessment feature adapts to industry trends, helping users pursue
relevant skill development and explore global job markets with cultural insights to support
international opportunities. The system includes a feedback mechanism to drive continuous
improvement, though it faces challenges in managing vast datasets and achieving precise cognitive
evaluations, which may impact the accuracy of its recommendations.

Neufeld et al. (2023) emphasize the significance of career choice as a pivotal decision impacting an
individual’s social, economic, and emotional well-being, echoing Gati and Kulcsar (2021) on the
complexities individuals face when answering, "What do I want to be when I grow up?" The
research highlights the importance of early career exploration, beginning in adolescence, and the
collaborative role played by family, friends, teachers, and guidance counselors in assisting students
through this decision-making process. Neufeld underscores the OECD's (2004) broad definition of
career guidance, which encompasses services that help individuals make informed educational,
training, and occupational choices throughout their lives. Importantly, Neufeld explores how
technology, including AI-powered tools, fits within this definition, providing support that
complements traditional career guidance practices. By integrating AI into instructional design and
career guidance, the study illustrates how these tools can enhance the ability of students to manage
their career paths effectively, positioning AI as an innovative and essential component in modern

14
career exploration strategies.

Dolhopolov et al. (2022) present a comprehensive study focused on utilizing artificial intelligence
(AI) systems to address the challenge of career guidance for prospective university students. The
research outlines the design and empirical testing of a Fully Connected Feed-Forward Neural
Network (FNN) model, developed to classify professional areas through multi-label classification.
The study includes the creation of a dataset composed of 29 input and 23 output parameters, with a
total of 936 data lines, demonstrating the dataset's suitability for training the neural network. The
authors detail a novel training method that emphasizes the neural network's capacity to reflect and
leverage internal connections for effective learning. Implemented using Python and employing key
libraries such as Keras, Numpy, and Pandas, this research contributes valuable insights into AI-
based career guidance systems. The findings provide a foundation for enhancing the development of
models that can evaluate and improve the skills and knowledge critical for successful career
development.

Westman et al. (2021) explore the current landscape and future potential of artificial intelligence
(AI) in supporting career guidance within higher education. They emphasize that the increasingly
dynamic nature of the labor market and the rising need for lifelong learning pose new challenges for
career guidance services. The authors argue that AI can play a significant role in bridging
educational services with employment needs, thereby enhancing career guidance practices. Through
focus groups, scenario-based workshops, and practical trials, the study identifies both the potential
benefits and obstacles associated with implementing AI in career guidance. These include the
ability of AI to support students in recognizing their skills, proposing study paths, and facilitating
job searches, while also assisting guidance staff by automating routine tasks and enabling more
personalized interventions. However, the authors also highlight barriers such as data accessibility,
ethical considerations, and the necessary competences for staff to effectively integrate AI tools.
Westman et al. conclude that AI, when designed to complement human agency, holds promise for
creating more adaptive, efficient, and accessible career guidance services.

John et al. have examined AI-driven models within career guidance systems, highlighting how
personalized recommendations can be effectively tailored to users' skills and aptitudes. The

15
literature underscores AI's role in identifying distinct career pathways, as algorithms process
extensive data to align career suggestions with individual personality traits, interests, and aptitudes.
Furthermore, studies advocate for dual-portals within these systems, designed to cater to both
parents and students, thereby creating a holistic support framework. Gamified assessments,
resembling MBTI-type models, are noted for enhancing engagement and precision in evaluating
user aptitudes. Additional research highlights the importance of financial planning and skill
development components, which address essential educational needs and improve the guidance
system’s effectiveness. Together, these studies provide a basis for a user-centric career guidance
system that not only suggests tailored career paths but also fosters skill-building and financial
awareness essential for sustained career success.

Wang et al. (2021) explore the role of machine learning in career counseling, examining current
trends and future directions within the field. The authors highlight that precision education, which
tailors learning approaches to individual student needs, has gained significant interest among
educators and policymakers. They emphasize that understanding students’ learning behaviors and
the impact of their individual differences on learning outcomes is crucial. Machine learning
provides a powerful tool for stakeholders to derive insights from educational data, enabling
predictive tasks that address various aspects of precision education, such as identifying at-risk
students and predicting drop-out rates. However, Wang et al. note that fewer studies focus on the
link between academic performance and career decisions. This gap underscores the need for
research that can enhance precision education by integrating predictions of students' career choices.
Their study evaluates the efficacy of predictive techniques in career decision-making and
demonstrates the feasibility of early detection. The findings offer valuable implications for theory
and methodology, suggesting that predictive modeling can enhance both educational and career
guidance practices.

Monreal et al. (2024) explored the role of Artificial Intelligence (AI) in enhancing career guidance
for secondary school students, especially within the context of the Philippines' K-12 education
system. The study recognized that students face challenges in selecting appropriate academic tracks,
a decision influenced by numerous personal and environmental factors. Leveraging AI in career
guidance could address these challenges by offering personalized and data-driven insights. Monreal

16
et al. identified that AI-based tools streamline the guidance process for counselors and allow
students to make more informed academic choices. Through a mixed-method approach, including
sentiment analysis and counselor interviews, the study revealed positive feedback regarding AI's
potential to improve decision-making accuracy, efficiency, and alignment with student goals.
Additionally, it highlighted that AI tools support career exploration, which can mitigate the negative
effects of misaligned career paths, such as dissatisfaction and limited advancement opportunities.

Dr. Deshpande, et al (2024) This study evaluates how Artificial Intelligence (AI) influences
education, focusing on its role in administration, instruction, and learning. AI has brought
significant changes to the field of education through its cognitive, adaptive, and decision-making
capabilities. Initially, AI was integrated into education via computers and related technologies. It
has since evolved into web-based and online intelligent education systems. Nowadays, AI-driven
robots and chatbots can perform tasks typically handled by educators, either independently or with
their assistance. These platforms enable educators to manage administrative tasks like reviewing
and grading assignments more efficiently and effectively, enhancing teaching quality. Additionally,
AI-powered systems use machine learning to personalize curriculum and content based on students'
needs. This personalization improves students' awareness, retention, and overall learning experience
by making it more interactive and tailored to individual preferences. The widespread adoption of AI
in education by institutions showcases its potential in transforming educational practices and
outcomes.

Wen et al. (2025) propose an advanced framework for predictive career guidance and
entrepreneurial development tailored to university students, utilizing Artificial Intelligence (AI) and
Machine Learning (ML). At the core of their study is the Wild Horse Optimized Resilient Extreme
Gradient Boosting (WHO-RXGBoost) model, a hybrid system integrating the robustness of
XGBoost with the dynamic search adaptability of the Wild Horse Optimization algorithm. This
model is engineered to deliver deeply personalized career and entrepreneurial recommendations by
processing complex datasets comprising demographic details, academic records, and extracurricular
involvement. The authors applied meticulous data preprocessing techniques, including noise
elimination, normalization through robust scaling, and dimensionality reduction using Principal
Component Analysis (PCA), thereby optimizing data quality and feature extraction. Performance
evaluations demonstrated WHO-RXGBoost’s superiority over traditional models, achieving 95%

17
accuracy, 93% precision, a 90% F1-score, and 91% specificity, confirming its predictive reliability.
Furthermore, user feedback indicated enhanced clarity, self-confidence, and alignment in career
planning and entrepreneurial interests. The research affirms the transformative potential of AI-
augmented decision support systems in creating responsive, scalable, and equitable guidance
infrastructures, offering a powerful solution to evolving student needs in navigating modern,
dynamic job markets and entrepreneurial landscapes.

Lakshmi et al. (2024) present an AI-Enhanced Career Guidance System designed to offer
personalized career pathways for university students, addressing the challenges of integrating
educational and occupational services in the era of lifelong learning. The study emphasizes the
underexplored potential of artificial intelligence in augmenting career counseling within higher
education institutions. Through methodologies including focus groups, scenario analyses, and real-
world experiments, the researchers gather insights from institutions, guidance personnel, and
students to identify the needs and applications of AI in career counseling. The findings highlight
the benefits of AI integration, such as improved accessibility to career services, enhanced
personalization of guidance, and support for continuous learning. However, the study also
acknowledges obstacles, including the need for robust data infrastructure and the importance of
addressing ethical considerations in AI deployment. Overall, the research contributes to the
evolving landscape of educational support systems by demonstrating how AI can be leveraged to
create scalable and adaptive solutions for career and entrepreneurial development challenges faced
by university students.

Vignesh et al. (2021) present an intelligent career guidance system that employs machine learning
to assist students in selecting the most suitable academic departments based on their individual skill
profiles. The proposed system is composed of three primary modules: a skill assessment module, a
prediction module, and a result analysis module. The skill assessment module integrates
psychological and technical skill-oriented questions to evaluate core competencies such as logical
reasoning, analytical thinking, mathematics, problem-solving, programming aptitude, creativity, and
hardware proficiency. These assessments are implemented using modern web technologies like
HTML5, CSS3, and JavaScript, providing an engaging and intuitive user interface. For predictive
analysis, the system utilizes the K-Nearest Neighbors (KNN) algorithm to classify students into
academic departments aligned with their skillset. Additionally, K-Means Clustering is used to group

18
departments by similarity, offering students secondary recommendations and improving
personalization. A Flask API serves as a bridge between the user-facing assessment tools and the
backend ML models developed in Python. The manually curated dataset used for training includes
over 500 entries with quantified skill metrics. With a predictive accuracy of over 90%, the system
demonstrates strong potential in redefining traditional career counseling frameworks by offering
intelligent, data-driven, and student-centric guidance solutions.

Westman et al. (2021) conduct a comprehensive investigation into the integration of Artificial
Intelligence (AI) within career guidance systems, focusing on the evolving demands of lifelong
learning and dynamic labor markets. Employing a multimethod research design—including focus
groups, scenario planning, and practical trials across Finnish higher education institutions—the
study identifies both opportunities and challenges associated with AI-enhanced guidance services.
Key findings reveal that students value AI for providing timely, personalized support in career
planning, self-management, and skill recognition. They envision AI as an embedded component of
daily learning activities, capable of offering proactive nudges and aligning individual competencies
with labor market requirements. Conversely, guidance staff perceive AI as a tool to augment their
roles, facilitating early intervention, automating routine tasks, and enabling more strategic
allocation of resources. The research introduces a maturity model delineating stages of AI adoption
in career services, ranging from AI-aware to AI-transformed guidance ecosystems. However, the
study also underscores significant barriers, including data accessibility, ethical considerations, and
the necessity for transparency in AI decision-making processes. The authors advocate for the
development of robust data infrastructures and ethical frameworks to ensure equitable and effective
AI integration. This work contributes valuable insights into the co-evolution of human and artificial
agents in educational guidance, emphasizing the need for collaborative, transparent, and ethically
grounded AI applications in career development contexts.

Kumar et al. (2021) propose a decision tree-based framework aimed at assisting students in
identifying suitable career paths by analyzing their individual strengths and weaknesses. The study
specifically targets students who may lack clear career goals but possess untapped potential,
providing a platform for self-assessment and goal setting. The decision tree model employed
facilitates the classification of students into appropriate career categories based on various
attributes, enabling personalized guidance. The authors conduct a performance evaluation to assess
the model's effectiveness in accurately predicting career paths, demonstrating its utility in

19
educational settings. This research contributes to the field by offering a data-driven approach to
career counseling, emphasizing the importance of personalized guidance in unlocking students'
potential and aiding them in achieving their career objectives. The framework's implementation
underscores the role of machine learning techniques in enhancing traditional career guidance
methods, providing a scalable solution to address the diverse needs of students in educational
institutions. By leveraging decision tree algorithms, the study offers a transparent and interpretable
model, facilitating its adoption by educators and counselors seeking to support students in their
career planning endeavors.

Al-Dossari et al. (2020) introduced "CareerRec," a machine learning-based recommendation

system aimed at assisting Information Technology (IT) graduates in selecting suitable career paths.
Trained on a dataset of 2,255 IT professionals from Saudi Arabia, the system focused on three core
career categories—Developer, Analyst, and Engineer—leveraging both technical and soft skills for
prediction. The authors implemented five machine learning algorithms, with XGBoost
outperforming others by achieving a notable accuracy of 70.47% following class imbalance
correction via oversampling. This enhancement significantly improved classification accuracy,
particularly for the underrepresented Engineer category. Unlike prior career guidance frameworks
that heavily relied on academic credentials or technical assessments alone, CareerRec presented a
more comprehensive model by incorporating multidimensional skill analysis, enabling nuanced
alignment of individual competencies with labor market requirements. The study demonstrates the
applicability and promise of ML in streamlining career counseling, especially in rapidly evolving
technology sectors. However, the researchers acknowledged certain constraints, such as the limited
dataset size and reliance on self-reported skill evaluations, which may introduce subjectivity. They
recommend future research to incorporate larger, more heterogeneous datasets and objective
assessment techniques to further improve the predictive robustness and generalizability of the
model.

Rangnekar et al. (2018) proposed a career prediction model utilizing data mining and linear
classification techniques to assist students in making informed career choices. The study
emphasized the integration of both academic and personal factors, including psychological
assessments, to enhance the accuracy of career predictions. By employing various data mining
algorithms, the researchers aimed to identify patterns and correlations between students' attributes

20
and suitable career paths. The model's performance was evaluated using standard metrics, revealing
that the Part classifier outperformed other techniques in terms of accuracy. This approach
underscores the significance of incorporating a comprehensive set of variables, such as aptitude and
personality traits, in career guidance systems. The research contributes to the field by
demonstrating the efficacy of data-driven methods in predicting career outcomes, thereby offering a
valuable tool for educational institutions and career counselors to support students in their
professional development.

Zhang et al. (2018) introduced a hybrid recommendation model that integrates collaborative
filtering with deep neural networks to enhance recommendation accuracy and address data sparsity
challenges. The model comprises two primary components: a feature representation module
utilizing a quadric polynomial regression (QPR) model to extract latent user and item features, and
a deep neural network (DNN) that predicts user-item ratings based on these features. The QPR
model improves upon traditional matrix factorization by capturing complex, nonlinear relationships
in the data, while the DNN component leverages these refined features to model intricate user-item
interactions. The authors evaluated their model on three public datasets— MovieLens-100K,
MovieLens-1M, and Epinions—demonstrating superior performance in terms of Mean Absolute
Error (MAE) and Root Mean Squared Error (RMSE) compared to baseline methods such as SVD,
PMF, and traditional collaborative filtering approaches. Notably, the model exhibited enhanced
prediction stability and accuracy, particularly in scenarios with high data sparsity. This work
underscores the potential of combining advanced feature extraction techniques with deep learning
architectures to overcome limitations of conventional recommendation systems, offering a robust
framework adaptable to various domains requiring personalized recommendations.

Kiran et al. (2018) proposed a data-driven recommendation system tailored to the Pakistani job
market, aiming to align individuals with suitable professions and requisite skills. Utilizing
Association Rule Mining (ARM) via the Apriori algorithm within R Studio, the researchers
analyzed a dataset of 250 records collected through surveys. This dataset encompassed variables
such as educational background, work experience, and skill sets. The ARM approach facilitated the
identification of frequent itemsets, leading to the generation of association rules that linked specific
profiles to corresponding professions and skill recommendations. For instance, the model could
suggest a career in quality assurance for individuals with particular educational and experiential

21
backgrounds, accompanied by relevant skill recommendations. The study's methodology involved
setting support and confidence thresholds to filter significant rules, ensuring the relevance and
reliability of the recommendations. Despite the model's promising framework, the authors
acknowledged limitations, notably the modest dataset size and potential biases due to self-reported
data. They advocated for future research to incorporate larger, more diverse datasets and to explore
additional data mining techniques to enhance the system's predictive accuracy and applicability
across broader contexts.

Roy et al. (2018) proposed a machine learning-based model for predicting suitable career paths for
students, focusing on the computer science domain. The study employed algorithms such as
Support Vector Machines (SVM), Decision Trees, and XGBoost, utilizing features like academic
scores, personality traits, and extracurricular activities. The results indicated that XGBoost
outperformed the other models in terms of accuracy. The authors emphasized the importance of
integrating various personal and academic factors to enhance the precision of career predictions.
They also highlighted the potential of such models to assist both students in making informed career
choices and recruiters in identifying suitable candidates. The study concluded that advanced
machine learning techniques could significantly contribute to the development of effective career
guidance systems.

Ade and Deshmukh (2014) introduced an innovative approach to predicting students' career
choices by employing an incremental ensemble of classifiers. This methodology integrates multiple
classifiers—such as Naive Bayes, Averaged One-Dependence Estimators (AODE), 3-Nearest
Neighbors, Non-Nested Generalized Exemplars (NNGE), and KStar—into a cohesive ensemble
using a voting mechanism. The ensemble operates incrementally, allowing it to adapt to new data
without retraining from scratch, which is particularly beneficial in dynamic educational
environments where student data evolves over time. The authors validated their approach by
conducting psychometric assessments on students, capturing various attributes including interests
and aptitudes. The incremental nature of the ensemble ensures that the model remains up-to-date
with the latest student information, thereby enhancing its predictive accuracy. This technique
addresses the limitations of traditional batch learning methods, which often struggle with scalability
and adaptability. By leveraging the strengths of multiple classifiers and facilitating continuous
learning, the proposed model offers a robust framework for career guidance systems. However, the

22
study acknowledges potential challenges such as the need for quality data and the computational
complexity associated with managing multiple classifiers. Future research could explore optimizing
the ensemble's components and extending its application to broader educational contexts.

Bao et al. (2009) presented a quantitative framework for analyzing individual career decision-
making by employing Partial Least Squares (PLS) regression. This statistical method is particularly
adept at handling multicollinearity and high-dimensional data, making it suitable for modeling the
complex relationships between various personal attributes and career choices. In their study, the
authors collected data encompassing factors such as personality traits, interests, and values, and
applied PLS regression to identify latent variables that significantly influence career decisions. The
model's strength lies in its ability to project both predictor and response variables into a new space
that maximizes covariance, thereby capturing the underlying structure of the data. The findings
demonstrated that PLS regression could effectively model the multifaceted nature of career
decision-making, offering insights into how different personal factors interact to influence career
choices. This approach provides a robust tool for career counselors and educators to understand and
predict career decision behaviors, facilitating more tailored guidance for individuals. However, the
study also acknowledges limitations, such as the need for larger and more diverse datasets to
enhance the generalizability of the model. Future research could expand on this work by integrating
additional variables and exploring longitudinal data to further refine the predictive capabilities of
the PLS regression model in the context of career decision-making.

Gallusser et al. (2019) conducted a retrospective study evaluating the efficacy of percutaneous
image-guided cryoablation (PCA) for managing painful bone metastases in patients unresponsive to
standard therapies. The study encompassed 16 patients with 18 metastatic lesions treated over a
five-year period. Pain relief was assessed using the Numerical Rating Scale (NRS), revealing a
significant reduction in mean scores from 3.3 to 1.2 post-procedure (p=0.0024). Notably, 75% of
patients experienced substantial pain alleviation, and 63% achieved local disease stability or no
recurrence at the treated sites. Additionally, five patients underwent concurrent long bone fixation
due to impending fractures, all reporting satisfactory pain relief at follow-up. The study
underscores PCA's potential as a safe and effective modality for pain palliation and local tumor
control in cases where conventional treatments have failed. However, the authors acknowledge
limitations, including the small sample size and retrospective design, suggesting the need for larger,

23
prospective studies to validate these findings and further refine patient selection criteria for optimal
outcomes.

Uddin and Lee (2016) introduced a predictive framework that correlates personality traits with
academic and career data to identify students best suited for specific educational and professional
paths. Utilizing the Big Five personality model—comprising openness, conscientiousness,
extraversion, agreeableness, and neuroticism—the study analyzed how these traits influence
academic performance and career alignment. The researchers employed machine learning
techniques to process and interpret the complex relationships between personality profiles and
academic outcomes. Their findings revealed that certain personality traits, notably
conscientiousness and openness, have a significant positive correlation with academic success,
while high levels of neuroticism tend to negatively impact performance. By integrating personality
assessments with academic data, the model provides a nuanced approach to predicting student
success and guiding career counseling. This methodology offers a more personalized strategy for
educational institutions to support students in making informed decisions about their academic and
career trajectories. However, the study acknowledges limitations, such as the need for larger and
more diverse datasets to enhance the model's generalizability. Future research could focus on
longitudinal studies to assess the long-term effectiveness of personality-based predictions in
educational and career planning.

M.-J. Nzengou-Tayo's 2016 article, "Ready to Burst," published in Caribbean Quarterly, offers a
nuanced exploration of the Caribbean's socio-political landscape, emphasizing the region's
susceptibility to systemic crises. The paper delves into the intricate interplay between historical
legacies, economic vulnerabilities, and political instability that collectively heighten the risk of
societal rupture. Nzengou-Tayo employs a multidisciplinary approach, integrating perspectives
from political economy, sociology, and cultural studies, to analyze the underlying factors
contributing to the region's precarious state. The study highlights how entrenched inequalities,
coupled with inadequate governance structures, exacerbate tensions and impede effective crisis
management. Furthermore, the article examines the role of external influences, such as global
economic shifts and international policy interventions, in shaping the Caribbean's trajectory toward
potential upheaval. Nzengou-Tayo's work underscores the urgency for comprehensive reforms
aimed at enhancing institutional resilience and fostering socio-economic equity to mitigate the risk

24
of collapse. The article's interdisciplinary methodology and critical analysis provide valuable
insights for scholars and policymakers seeking to understand and address the complex challenges
facing the Caribbean region.

S. Abdulrasoul and M. Puglisi-Weening's 2017 review, "Review of Toxicology in the Middle

Ages and Renaissance," published in the Journal of Natural Products, offers a scholarly examination
of the evolution of toxicological knowledge during the medieval and Renaissance periods. The
authors delve into the contributions of seminal figures such as Paracelsus, who introduced the
concept that "the dose makes the poison," emphasizing the importance of dosage in determining
toxicity. Additionally, the work of Moses Maimonides is discussed, particularly his "Treatise on
Poisons and Their Antidotes," which provided systematic approaches to identifying and
counteracting poisons. The review also highlights the practices of notorious poisoners like the
Borgias and the use of substances such as arsenic and mercury in political intrigue. Furthermore,
the paper examines the intersection of toxicology with other disciplines, including alchemy and
medicine, during this period. The authors underscore the significance of these historical insights in
shaping modern toxicological science and highlight the importance of understanding historical
perspectives to inform contemporary practices.

25
2.2 Comparative study (Of Different Papers by using Table)-

S. Title Author Publication Methodology Year

No.
1. AI-Enhanced Youth Seyedali Ahrari, IGI Global • Mixed- 2024
Career Guidance by Zeinab Methods
Mapping Future Zaremohzzabieh, Analysis
Employment Paths Rusli Abdullah • Diverse
with Theory and Youth Data
Practical Collection
Application
• AI Data
Modeling
2. Cloud-Based And AI Kehinde Hussein Lawal, 15th Annual ICT for • Descriptive 2024
Enabled Career Path: Shiynsa Charles Africa Conference Survey
A Meeting Point For Lwanga (2024) Design
Students, Parents, • Multistage
Higher Institution Sampling
And Industries
• Questionnai
res
3. Sarah Bankins, Journal of Vocational 2024
Navigating career • Systematic
Stefan Jooss, Simon Behavior
stages in the age of Literature
artificial intelligence: A Lloyd, D. Restubog, ReviewImage
Mauricio Marrone,
systematic matching
interdisciplinary review Anna • Bibliometric
and agenda for future Carmella Ocampo, Analysis
Mindy Shoss
research
• Thematic
Analysis
4. Artificial Egle Gedrimiene, Education and 2024
• Research
Intelligence (AI)- Ismail Celik, Antti Information
Design
enhanced learning Kaasila, Kati Technologies
analytics (LA) for Mäkitalo & Hanni • Data
supporting Career Muukkonen Collection:
decisions:
advantages and • Data Analysis
challenges from
user perspective.

26
5. Use of Jocelle B Monrel, Brookfield 2024
• Systematic
Artificial Thelma Palaoag Academic
Review
Intelligence Limited
in Career • Interviews
Guidance:
Perspectives • Sentiment
of Secondary Analysis
Guidance
Counselor
6. Leveraging Md Zarif International 2024
• Data
Artificial Rahman Journal of
Intelligence for Career Collection
Enhanced Development • Analysis of
Career Digital Skills
Guidance and
Initiatives
development in
Bangladesh: • Recommendati
Addressing ons Based on
Educational and Findings
Employment
Gaps.

7. The AS Sathish, V Samuel .IEEE Computer • Data 2024

Significance of Rajkumar, Vihas Vijay, Society Collection
Artificial Chinnadurai Kathiravan • AI Algorithm
Intelligence in Implementatio
Career n
Progression • Validation and
and Career Testing
Pathway
Development

8. Enhancing IEEE 2024

• Data
Career Sonali J Mahure, B Computer
Collection &
Pathways: Rajalakshmi, T Eesha Society
Preprocessing
Advancing Manohar, SR
Guidance Vaishnavi, Nancy • Algorithmic
Systems with Priya Model
XGBoost Implementatio
Algorithm n
• System
Evaluation &
Feedback
Mechanism

27
 9. Supporting Paul Neufeld AI-Enhanced 2023
• Comparative
Career Instructional
Analysis:
Exploration Design
Evaluation of
and Guidance
AI-powered
with AI-
tools
Powered
• Experimental
User Testing
• Content
Analysis
10. Use of Serhii IEEE Computer 2022
• AI Models:
artificial Dolhopolov, Society
Use of machine
intelligence Tetyana learning
systems for Honcharenko,
determining Svitlana • Data
the career Anastasiia Collection
guidance of Dolhopolova, • Validation
future Olena
university
Riabchun,
student
Maksym
Delembovskyi,
Oksana
Omelianenko
11. Artificial Stina Westman, IAFOR Journal 2021
• Focus Group
Intelligence Janne Kauttonen, of Education
for Career Aarne Klemetti, • Scenario
Guidance-- Niilo Korhonen, Workshops
Current Milja Manninen, • Practical Trials
Requirement Asko Mononen,
s and Salla Niittymäki,
Prospects for Henry Paananen
the Future.
12. AI based Firdosh sayyed, Fast Track 2020
• Neural
Career Ronak Sanghani, Publications
Network
Guidance Abhishek Vora, Architecture
Nikita Lemos
• Clustering and
Association
Rules
• Myers-Briggs
Type Indicator
(MBTI)

28
13 Machine Wang, L., & The Journal of 2021
• Gaussian
learning in Chen, X. Career
Bare-Bones
career Assessment
counseling: • CBBOA-SVM
Current Optimization
trends
• Communicatio
and future
n mechanism
directions

14 Beyond Jingyi Duan, International 2024

• Foundations
Traditional Suhan Wu Journal of New
and Theories
Pathways: Developments in
Leveraging Education • Assessment
Generative Approach
AI for
• Opportunities
Dynamic
and Challenges
Career
Planning in
Vocational
Education
15. Impact of AI Dr. Deshpande International 2024
• Literature
on A.S.1, Dr. Journal on
Analysis
Education: A Mahajan S.R.2, advance
Review Dr. Kulkarni engineering and • Case Studies
S.B.3, Prof Puri management. and System
S.A Evaluation
• Comparative
Analysis
16. Career Ayush Chandrol; IEEE 2024
• Focus Groups
Counselling Monisha Awasthi; and Scenario
using AI in Deepak Sharma; Work
the field of Mani Kansal;
IT Industry Komal Sharma; • Practical Trials
in Dynamic Ankur Goel • Data Mapping
Environment
and Analysis

17. Applying HeeWon Hong , Education and 2024

• Program
artificial YeonK young Information
Design
intelligence in Kim Technologies
career education • Implementatio
for students n
with intellectual
• Evaluation
disabilities: The
effects on career
self-efficacy
and learning
flow

29
18. The promises Celik, I., Dindar, Technology 2022
• Literature
and M., Muukkonen, Trends
Review
challenges of H., & Järvelä, S.
artificial • Data Analysis
intelligence
• Challenge
for teachers:
Identification
A systematic
review of
research
19. Transparency Gedrimiene, E., Journal of 2023
• Data
and Celik, I., Learning
Collection
trustworthine Mäkitalo, K., & Analytics
ss in user Muukkonen, H. • Survey and
intentions to Evaluation
follow career
• Data Analysis
recommendat
ions from a
learning
analytics tool
20. The impact S. Bhatia & K. International 2020
• Data
of artificial Kaur Journal of
Collection
intelligence Educational
on career Management. • Machine
guidance: A Learning
review Techniques
Application
• Outcome
Analysis and
Intervention
Design

30
 CHAPTER - 3

3.1 Problem Statement

Career guidance is a critical component of educational and professional development, yet many
individuals struggle to find the right career path that aligns with their skills, interests, and long-term
goals. Traditional career counseling methods often lack personalization and may not fully account
for an individual’s unique profile, including their aptitude, aspirations, abilities, and past
experiences. In this project we would develop an AI-powered career guidance system that provides
personalized career pathways for students and professionals. The system Would consider an
individual’s aptitude, aspirations, abilities, and work experience to recommend tailored career
options and future progression opportunities. Key Areas to Address:
o Aptitude Assessment: The system should include AI-driven tools to assess an individual’s natural
aptitudes and strengths, identifying the areas where they are most likely to succeed and find
satisfaction in their work.
o Aspirations and Interests: Incorporate methods to capture and analyze the user’s career
aspirations, interests, and values, ensuring that the recommendations align with their long-term
goals and passions.
o Ability and Experience Mapping: The system should evaluate the user’s current abilities, skills,
and experiences, mapping these against potential career paths to identify where they stand and what
further development might be needed.
o Future Progression and Skill Gaps: Use predictive analytics to identify potential future career
progression opportunities based on industry trends and individual growth potential. The system
should also highlight any skill gaps and suggest targeted learning opportunities to help users
advance.
o User-Friendly Interface: Develop an intuitive, user-friendly interface that makes the career
guidance process accessible and engaging for users at all levels, from students exploring initial
career options to professionals considering a change or advancement.

3.2 Proposed Methodology -:

1. User Profile Creation & Data Collection

31
• Front-End: User fills out a form with basic information (age, education, work experience) and
uploads a resume (optional).
• Back-End: Data is stored in a database and normalized for further processing.
• User Preferences: The system asks users about their career interests and aspirations through forms
or questionnaires (e.g., via RIASEC, MBTI models, or open-ended questions).
• Data Processing: NLP models process text input to extract key information related to interests,
skills, and aspirations.

2. Aptitude and Skills Assessment

• Front-End: Users complete skills assessments (e.g., problem-solving tests, personality quizzes,
technical skills tests).
• Back-End: The responses are scored and analyzed by pre-trained AI models.
o Cognitive and personality-based tests use predefined scoring systems.
o Skills assessment data (e.g., coding proficiency, communication) is mapped to industry-standard
skills using a skills ontology.
• AI: Based on quiz results, AI models map users’ aptitudes to specific career categories (e.g.,
technical, creative, leadership roles).

3. Career Path Recommendations

• Front-End: Once data is collected, the system generates a list of recommended career paths.
• Back-End:
o Collaborative Filtering: The system compares the user’s profile to others with similar aptitudes,
interests, and aspirations to recommend careers they might enjoy.
o Content-Based Filtering: The system analyzes career path data (e.g., job descriptions, skill
requirements) and compares it with the user’s profile to suggest the best-fitting careers.
• AI Models: The system ranks the careers based on compatibility, user interests, skill level, industry
trends, and potential for growth.

4. Skill Gap Analysis and Progression Path

• Front-End: The system shows the user a visual representation of their current skills and identifies
gaps for desired careers.
• Back-End:

32
o Skill Gap Detection: The AI compares the user’s existing skills to the required skills for the
recommended careers. It uses machine learning models to identify missing competencies and
suggests learning resources.
o Future Progression Path: AI uses predictive analytics (time-series forecasting, regression models)
to suggest potential career growth paths over time (e.g., from entry-level to senior-level roles) based
on industry data.
• Recommendation Engine: Suggests courses, certifications, and learning resources (integrating
external APIs like Coursera, Udemy).

5. Career Insights and Industry Trends

• Front-End: Users can view up-to-date insights on their selected career paths, including growth
projections, salary estimates, and emerging skills.
• Back-End:
o Industry Trend Analysis: Machine learning models analyze current market data (from external
APIs) to predict demand in specific industries, emerging job roles, and evolving skills.
o Salary Predictions: Using historical job market data, the system predicts average salary ranges for
different roles in various regions.

6. Personalized Action Plan

• Front-End: The user is provided with a personalized action plan that includes career
recommendations, skill-building resources, and a timeline for career progression.
• Back-End:
o Action Plan Generation: Based on the career recommendations and skill gap analysis, the system
generates an individualized action plan.
o Notification System: Sends periodic updates to users about their progress and reminders to take the
next steps (e.g., "Complete this course to fill your skill gap in data analysis").

33
 FIG – 2 Workflow Diagram

3.3 Methodology Used:

The AI-driven career guidance system employs a systematic approach that incorporates Machine
Learning (ML), Natural Language Processing (NLP), Learning Analytics (LA), and Big Data to
provide tailored career recommendations. This methodology is constructed to be scalable, adaptive,
and grounded in data, thereby facilitating real-time responsiveness to fluctuations in job market
trends. The methodology encompasses several essential phases, which are outlined as follows:

3.3.1 System Architecture

The AI-enhanced career guidance system is structured around four primary components:

1. User Profiling Module – This component is responsible for the collection of user data,
encompassing skills, interests, educational background, and personal preferences.

34
2. AI-Based Career Matching Engine – This engine employs machine learning models to forecast
the most appropriate career trajectories for users.

3. Real-Time Job Market Analytics – This component integrates analyses of industry demand to
enhance the accuracy of career recommendations.

4. Skill Gap Analysis & Personalized Learning Pathways – This module proposes relevant
courses and certifications aimed at addressing identified skill deficiencies.

Fig. 3: AI Career Guidance System Architecture

3.3.2 Data Collection and Preprocessing

In order to deliver precise career recommendations, the system is predicated on three principal data
sources:

User Data Collection: Users provide information regarding their educational qualifications, skills,
work experience, and career aspirations. Additionally, AI-driven self-assessment tests evaluate
cognitive abilities, interests, and personality characteristics.

35
Job Market Data Integration: The system aggregates job postings, skill trends, and salary
information from platforms such as LinkedIn, Indeed, and Glassdoor.

Skill Demand Analysis: Utilizing Big Data and Predictive Analytics, the system identifies skills
that are in high demand and emerging job roles.

Table 3: Data Sources and Their Role in Career Guidance

3.3.3 AI-Based Career Matching Model

The career matching engine utilizes Machine Learning (ML) and Natural Language Processing
(NLP) to produce tailored recommendations. This process is executed in multiple stages:

Step 1: User Profiling and Data Encoding

User data is transformed into vector representations utilizing the Term Frequency-Inverse
Document Frequency (TF-IDF) method for textual inputs. Numeric attributes, such as age,

36
experience, and skill ratings, are subjected to normalization to ensure consistency across the dataset.
Subsequently, feature selection is performed to eliminate irrelevant parameters from the final
dataset.

Step 2: Machine Learning-Based Career Classification

Supervised learning algorithms, including Decision Trees, Support Vector Machines, and Neural
Networks, are employed to categorize users into distinct career classifications. Additionally,
unsupervised learning techniques, specifically clustering, are utilized to uncover latent patterns
within user profiles.

AI Model Purpose Accuracy (%)

Decision Tree 94.1%

Career classification based on skills

Support Vector Machine (SVM)

Career field prediction 99.5%

Random Forest Skill gap analysis 86.0%

Neural Networks Personalized career 98.0%

suggestions

Table 4: AI Models Used for Career Guidance

3.3.4 Model Workflow and Implementation

The AI-driven career guidance system operates according to a systematic workflow designed to
process user data and generate career recommendations. The workflow is depicted in Figure 2 and
is elaborated upon in the following sections:

37
 FIG 4: Workflow of Proposed Model

Data Acquisition and Preprocessing

Initially, the dataset is obtained and formatted to meet the requirements of machine learning
applications.

Dataset Partitioning

The dataset is partitioned into 80% for training purposes and 20% for testing, facilitating the
training and validation of the model.

Data Preprocessing

38
This phase involves the selection of relevant features, the cleaning of textual data, and the encoding
of categorical variables

Training the Decision Tree Classifier Model

The Decision Tree Classifier is selected for its interpretability and effectiveness in classification
tasks. The model is trained utilizing the following hyperparameters:

Criterion: Gini Index

Maximum Depth: 15

Minimum Samples Split: 2

Minimum Samples Leaf: 1

Random State: 42

Hyperparameter Optimization

The model undergoes optimization through Grid Search Cross-Validation (CV), refining the
parameters as follows:

Criterion: {Gini, Entropy}

Maximum Depth: {5, 10, 15, 20}

Minimum Samples Split: {2, 5, 10}

Minimum Samples Leaf: {1, 2, 4}

Model Evaluation

39
The performance of the trained model is assessed using the validation dataset, resulting in the
following metrics:

Model Accuracy Score: 94.11%

Training Set Accuracy Score: 94.45%

Model Preservation

The final trained model is saved as a pickle file, facilitating its deployment within the AI career
guidance system.

3.3.5 Results and Evaluation

The model underwent testing utilizing a dataset comprising 10,000 job seekers. A comparative
analysis was conducted between the AI-generated recommendations and conventional counseling
approaches, yielding the following outcomes:

An accuracy rate of 85% in career predictions, significantly reduced response times (AI: seconds,
Human counselors: days), and enhanced user satisfaction levels (AI: 88%, Traditional methods:
62%).

Aspects Artificial Intelligence Traditional Methods

Response Seconds. Days

Time

User 88% 62%

Satisfaction
levels

Table 5: Aspects

40
 CHAPTER – 4

4.1 Discussion -:

Machine Learning Algorithms for an AI Career Guidance System

To build a robust and scalable AI Career Guidance System, multiple machine learning algorithms
are required. Each algorithm addresses specific tasks like classification, prediction, clustering, and
natural language processing. Here's a detailed overview of the algorithms and their use cases:

1. Classification Algorithms

Logistic Regression

⦁ Purpose: Classify users into predefined career categories based on their skills, interests, and
aptitude test results.

⦁ Use Case:

o Predict career fields (e.g., Data Science, Engineering, Marketing).

o Determine career recommendations for new users.

⦁ Advantages:

o Simple and interpretable.

o Works well with linearly separable data.

⦁ Formula:

P(y=1∣X) = 1/(1+e-(wX+b))

Random Forest

⦁ Purpose: Handle multi-class classification tasks with high accuracy.

41
⦁ Use Case:

o Predict career paths by analyzing user attributes like skills, aptitude scores, and experience.

⦁ Advantages:

o Handles missing data and non-linear relationships.

o Provides feature importance for model interpretability.

⦁ Diagram: A collection of decision trees combined using bagging for robust predictions.

Support Vector Machines (SVM)

⦁ Purpose: Identify the best career fields by separating data points into hyperplanes.

⦁ Use Case:

o Distinguish overlapping career paths based on complex features.

⦁ Advantages:

o Effective in high-dimensional spaces.

o Kernel tricks allow solving non-linear problems.

2. Regression Algorithms

Linear Regression

⦁ Purpose: Predict continuous variables like salary, skill scores, or job satisfaction.

⦁ Use Case:

o Estimate expected salary based on skills and career field.

o Analyze the impact of additional certifications on career progression.

42
⦁ Formula: y = wX+b

Gradient Boosting Regression (e.g., XGBoost)

⦁ Purpose: Predict future career growth or skill improvement.

⦁ Use Case:

o Analyze the likelihood of promotions or career switches.

⦁ Advantages:

o Handles outliers and complex non-linear patterns.

3. Clustering Algorithms

K-Means Clustering

⦁ Purpose: Group users with similar skill sets or interests into clusters.

⦁ Use Case:

o Identify career categories for users with no predefined goals.

o Suggest courses or training programs to similar user clusters.

⦁ Formula: J = ∑ni=1∑kj=1|| xi(j)- cj||2

Hierarchical Clustering

⦁ Purpose: Create a dendrogram to understand hierarchical relationships among career paths.

⦁ Use Case:

43
 o Analyze how different career fields overlap or diverge.

4. Natural Language Processing (NLP) Algorithms

BERT (Bidirectional Encoder Representations from Transformers)

⦁ Purpose: Analyze user-written responses about career goals.

⦁ Use Case:

o Extract insights from open-ended responses in career counseling.

o Match career aspirations to industry requirements.

⦁ Advantages:

o Handles context-rich data.

o Pre-trained on large corpora for accuracy.

TF-IDF (Term Frequency-Inverse Document Frequency)

⦁ Purpose: Rank career keywords in job descriptions.

⦁ Use Case:

o Identify trending skills in job market data.

5. Recommendation Algorithms

Collaborative Filtering

⦁ Purpose: Suggest careers or courses based on user similarities.

⦁ Use Case:

44
 o Recommend career paths by analyzing the choices of similar users.

⦁ Advantages:

o Effective in personalized recommendations.

⦁ Formula:

Similarity(A,B)= ∑ni=1(Ai-A’) (Bi-B’)/√( ∑ni=1(Ai-A’)2). √( ∑ni=1(Bi-B’)2)

Content-Based Filtering

⦁ Purpose: Match careers to users based on skills and interests.

⦁ Use Case:

o Suggest job roles aligned with user attributes.

6. Dimensionality Reduction Algorithms

Principal Component Analysis (PCA)

⦁ Purpose: Reduce high-dimensional data into meaningful features.

⦁ Use Case:

o Visualize skill and aptitude data.

o Preprocess features for clustering and classification models.

7. Reinforcement Learning Algorithms

Q-Learning

45
⦁ Purpose: Optimize career recommendations over time.

⦁ Use Case:

o Suggest incremental career steps based on past user behavior.

8. Ensemble Learning Algorithms

AdaBoost

⦁ Purpose: Combine weak classifiers to form a strong predictive model.

⦁ Use Case:

o Enhance prediction accuracy for career field classification.

⦁ Advantages:

o Reduces overfitting and improves performance on noisy data.

Stacking

⦁ Purpose: Combine predictions from multiple base models.

⦁ Use Case:

o Merge recommendations from classification and regression models.

9. Time-Series Prediction

Long Short-Term Memory (LSTM)

⦁ Purpose: Predict trends in job markets or career satisfaction over time.

46
⦁ Use Case:

o Forecast job availability and salary trends in specific industries.

⦁ Advantages:

o Handles sequential data with long-term dependencies.

How Our System Overpowers These Systems

1. Unique Gamified Aptitude Testing:

o Our system includes gamified tests to evaluate interests, personality traits, and
competencies, creating a more engaging and accurate assessment.

2. Skill Gap Analysis:

o Unlike others that primarily recommend jobs, our system identifies specific skill
deficiencies and provides actionable plans for improvement.

3. Dynamic and Real-Time Insights:

o Integrates dynamic career mapping with real-time job market trends, which many existing
tools lack.

4. Comprehensive Recommendations:

o Suggests a complete career development pathway, including courses, certifications, and

industry trends, rather than standalone services like resume building or interview prep.

5. Dual Interfaces for Parents and Students:

o Offers separate modules for students and parents, with parents receiving financial planning
assistance alongside career guidance.

6. Scalability and Regional Focus:

47
 o Designed for scalability across languages and geographies with features tailored for diverse
socio-economic backgrounds.

4.1.1 Model Evaluation and Performance Metrics

With a high classification accuracy of 95.39%, the trained Decision Tree Classifier proved to be
capable of successfully identifying underlying skill patterns. This impressive accomplishment can
be ascribed to:

i. Feature Engineering Excellence: Prediction accuracy is greatly influenced by the best possible
selection and preprocessing of pertinent attributes.

ii. Hyperparameter Optimization: By carefully adjusting splitting criteria and depth limitations,
decision boundary construction is improved.

iii. Robust Data Processing: By removing redundancies and inconsistencies, the model is
guaranteed to generalize effectively across a range of skill level

4.1.2 Confusion Matrix and Classification Matrix

By identifying the examples that were properly and wrongly predicted, the confusion matrix offers
a detailed perspective of categorization performance:

48
Where:

• True Positives (TP): Positive cases that are correctly identified.

• False Positives (FP): Positive cases that are incorrectly classified.

• False Negatives (FN): Negative cases that are incorrectly labeled.

• True Negatives (TN): Negative cases that are correctly classified.

The classification metrics shown below were calculated:

Evaluation Metrics Value

49
 Accuracy 95.39%

Precision 94.85%

F1-Score 95.12%

Recall 95.01%

These results support the model's practicality in skill evaluation settings by demonstrating its ability
to produce high-confidence predictions with few misclassifications.

FIG 5: Matrix

4.1.3. Dataset Perspectives

The information used in this study was meticulously organized to guarantee that different skill
levels were represented fairly.

4.1.3.1. Class Balance and Data Distribution:

50
• To provide equal representation across all competency groups, the dataset includes five
proficiency levels (Label Encoding Mappings: 0 = No Knowledge, 1 = Beginner, 2 = Intermediate,
3 = Proficiency, 4 = Advanced, and 5 = Expert).

• To ensure that no class dominates too much and to avoid bias in the decision tree learning
process, class imbalance analysis was carried out.

• By displaying the range of skill levels, the distribution plot verifies the dataset's objectivity and
diversity.

FIG 6: Distribution of Actual Career roles

4.1.3.2 Attribute selection and feature engineering:

• A variety of skill qualities, including cybersecurity, AI/ML, business analysis, troubleshooting,

networking, etc., are included in the dataset. To improve model performance, preprocessing
procedures included addressing missing data, encoding category variables, and normalizing
numerical features.

51
4.1.3.3. Attribute analysis and feature influence:

Analysis of Correlation Matrix

Significant relationships are revealed by the correlation matrix, which sheds light on the
interdependencies of technical competencies:

Strong Correlations:

• Software Engineering & Business Analysis (0.65): Indicates a convergence of technical and
analytical abilities.

• AI/ML & Data Science (0.58): Highlights how machine learning applications in data analytics are
interconnected.

• Cybersecurity & Forensics (0.56): Emphasizes how forensic investigations and security threat
mitigation are related.

Weak Correlations:

• Networking & Business Analysis (0.29): Shows that business strategy and network architecture
are not very dependent on one another.

• Graphics Design & Database Fundamentals (0.26): Makes a strong case for separating the fields
of database administration and creativity.

These findings support the idea that some skill clusters support one another while others function
largely independently, directing the development of organized competencies.

52
 FIG 7: Correlation Matrix of Numerical

4.1.3.4. Analysis of Feature Importance:

The relative significance of several features to the model's decision-making process is highlighted
by the feature importance plot.

Important Points to Note:

• Most Important Elements:

o Troubleshooting Skills (Highest Weightage): Indicates the need for diagnostic proficiency in all
technical fields.

53
The industry's increasing dependence on security experts is shown in the high predictive influence
of cybersecurity and forensics.

o AI/ML & Data Science: Highlights how computational intelligence is necessary for contemporary
skill frameworks.

o Technical Communication: Highlights how important clear technical articulation is in work

environments.

• Less Important Elements:

o Networking and Distributed Computing: Showed lower relative weights, perhaps as a result of
knowledge overlap or dataset limitations.

These results validate the model's interpretability and applicability by reaffirming the congruence
between model driven insights and actual industry expectations.

FIG 8: Feature Importance

54
 FIG 9: 3D Visualization of Feature Importance

4.1.4. Trends in Model Training and Performance:

4.1.4.1 Analysis of Overfitting and Training Convergence:

55
To avoid overfitting, the training process was closely observed. Among the observations are the
following:

• The confusion matrix shows few incorrect classifications, with rates falling below reasonable
bounds.

• Structure of Decision Trees:

o Top-level nodes emphasize cybersecurity, AI/ML, and troubleshooting abilities, confirming their
importance in expert evaluations.

o Branches at lower levels improve skill classification, allowing for accurate proficiency
differentiation.

FIG 10: Binary tree

56
4.1.5. Important Lessons and Industry Consequences:

4.1.5.1 Model Performance Insights:

With a high classification accuracy of 95.39 percent, accurate skill-level forecasts are guaranteed.

Feature Importance Alignment → Strengthens competency hierarchies that are pertinent to the
industry.

Strong model generalization capabilities are validated by minimal overfitting.

Potential for Scalability → Flexible enough to be incorporated into more extensive frameworks
for workforce assessments.

4.1.5.2 Practical Uses

Career Guidance Systems: Automating skill evaluations to prepare for the labor market.

HR & Recruitment Analytics → Finding the best applicants by matching their competencies.

Optimizing the Educational Pathway → Suggesting customized upskilling techniques.

Corporate Workforce Development → Improving training and tracking of employee competencies.

57
4.2 Result

Fig. 11 Confusion Matrix (With Decision Tree Classifier)

58
59
60
61
62
63
64
FIG. 12 -: Code

65
FIG. 13-: UI/UX Code

66
FIG 14-: Front Pages

67
68
FIG. 15 -: Dataset Insights

69
70
 FIG. 16: DJango pages

As we can see in these figures -:

• Decision Tree classifier -

Model Accuracy Score- 94.11

Training set accuracy score-94.45

Feasible

• Gaussian Naive Bayes-

Model Accuracy - 100

Training set accuracy - 100

Not Feasible

71
• Random Forest Classifier -

Model Accuracy Score-86.09

• KNN-

Model Accuracy Score-87.84

Training accuracy score -100

Not Feasible

• SVM-

Model Accuracy Score- 99.50

Model Accuracy Score with linear kernel & C=1.0 - 100

Model Accuracy Score with polynomial kernel- 100

Not Feasible

72
 CHAPTER –5

5.1 Conclusion

The AI-Enhanced Career Guidance System offers a revolutionary approach to career counseling,
tailored to the demands of the modern labor market. Unlike traditional methods, which often rely on
outdated diagnostics and generic information, this AI-powered model uses big data to provide
personalized career advice. It takes into account individual skills, preferences, market trends, and
future job prospects, offering students a more comprehensive and relevant career path.

By incorporating AI, the system can continuously update and adapt, ensuring that the advice it
provides aligns with the latest market developments. This dynamic approach benefits not only
students but also parents, educational institutions, and industries. Parents gain insights into job
market trends, enabling them to support their children's career choices. Educational institutions can
tailor their curricula to meet market demands, ensuring that graduates are well-prepared for the
workforce. Industries, on the other hand, can identify and recruit talent that matches their evolving
needs.

The cloud-based nature of the AI-Enhanced Career Guidance System ensures accessibility and
scalability, making it available to a broad audience. Students can access the system anytime and
anywhere, allowing for continuous career exploration and planning.

This study effectively illustrates a high-accuracy, interpretable classification model designed for
talent evaluation and competence assessment. The vital role that troubleshooting, cybersecurity, and
AI/ML abilities play in modern technical competencies is highlighted by their high predictive
importance. The model proves to be a strong analytical tool with great potential for structured
learning paths and real-world talent assessment, with an accuracy of 95.39%.

73
5.2 Future Work

The future work for AI-Enhanced Career Guidance Systems involves several exciting avenues that
can further improve career counseling and planning. Here are the key areas of focus:

1. Advanced Personalization: Future research can explore even more advanced AI algorithms to
provide highly personalized career advice. This could involve deeper analysis of individual learning
styles, preferences, and long-term career goals to create even more tailored recommendations.

2. Interdisciplinary Integration: Combining AI with other emerging technologies like blockchain

for secure data management and virtual/augmented reality for immersive career exploration
experiences can be a promising area of future work. This integration can create more engaging and
secure platforms for career guidance.

3. Ethical AI Use: Ensuring that AI systems are used ethically, with transparency and fairness, is
critical. Future work should focus on developing ethical frameworks and guidelines to prevent
biases and ensure equitable access to career guidance for all users, regardless of their background.

4. Longitudinal Studies: Conducting long-term studies to track the effectiveness of AI-enhanced

career guidance over time will provide valuable insights. This can help in understanding how these
systems impact users' career paths and success, leading to continuous improvements.

5. Scalability and Accessibility: Expanding the reach of AI-enhanced systems to underserved and
remote areas will be a crucial step. Future work should focus on developing scalable solutions that
can be accessed by a diverse population, ensuring that high-quality career guidance is available to
everyone.

74
 References

[1] Seyedali Ahrari, Zeinab Zaremohzzabieh, Rusli Abdullah (2024). AI-Enhanced Youth Career
Guidance by Mapping Future Employment Paths with Theory and Practical Application. Source
Title: Exploring Youth Studies in the Age of AI.
[2.] Kehinde Hussein Lawal, Shiynsa Charles Lwanga (2024). CLOUD-BASED AND AI-
ENABLED CAREER PATH: A MEETING POINT FOR STUDENTS, PARENTS, HIGHER
INSTITUTION AND INDUSTRIES. Source Title:ictforafrica.org
[3.] Sarah Bankins, Stefan Jooss, Simon Lloyd, D. Restubog, Mauricio MarroneAnna Carmella
Ocampo, Mindy Shoss (2024). Navigating career stages in the age of artificial intelligence: A
systematic interdisciplinary review and agenda for future research. Source Title: Journal of
Vocational Behavior
[4.] Egle Gedrimiene, Ismail Celik, Antti Kaasila, Kati Mäkitalo & Hann Muukkonen (2024).
Artificial Intelligence (AI)-enhanced learning analytics (LA) for supporting Career decisions:
advantages and challenges from user perspective. Source Title: Education and Information
Technologies.
[5.] Jocelle B Monrel, Thelma Palaoag (2024). Use of Artificial Intelligence in Career Guidance:
Perspectives of Secondary Guidance Counselor. Source Title Nanotechnology Perceptions.
[6.] Md Zarif Rahman (2024). Leveraging Artificial Intelligence for Enhanced Career Guidance and
development in Bangladesh: Addressing Educational Employment Gaps. Source Title: International
Journal of Career Development.
[7.] AS Sathish, V Samuel Rajkumar, Vihas Vijay, Chinnadurai Kathiravan (2024). The
Significance of Artificial Intelligence in Career Progression and Career Pathway Development.
Source Title: AI-Oriented Competency Framework for Talent Management in the Digital Economy
[8.] Sonali J Mahure, B Rajalakshmi, T Eesha Manohar, SR Vaishnavi, Nancy Priya(2024).
Enhancing Career Pathways: Advancing Guidance Systems with XGBoost Algorithm. Source Title:
4th International Conference on Pervasive Computing and Social Networking (ICPCSN)
[9.] Paul Neufeld (2023). Supporting Career Exploration and Guidance with AI-Powered Tools.
Source title: AI-Enhanced Instructional Design
[10.] Serhii Dolhopolov, Tetyana Honcharenko, Svitlana Anastasiia Dolhopolova, Olena Riabchun,
Maksym Delembovskyi, Oksana Omelianenko (2022). Use of artificial intelligence systems for
determining the career guidance of future university student. Source Title: International Conference
on Smart Information Systems and Technologies (SIST)

75
[11.] Stina Westman, Janne Kauttonen, Aarne Klemetti, Niilo Korhonen, Milja Manninen, Asko
Mononen, Salla Niittymäki, Henry Paananen (2021). Artificial Intelligence for Career Guidance--
Current Requirements and Prospects for the Future. Source Title: IAFOR Journal of Education.
[12.] Firdosh sayyed, Ronak Sanghani, Abhishek Vora, Nikita Lemos (2020). AI based Career
Guidance. Source Title: International Research Journal of Engineering and Technology (IRJET)
[13.] Wang, L., & Chen, X. (2021). Machine learning in career counseling: Current trends and
future directions. Source Title: Journal of Career Assessment
[14.] S. Bhatia & K. Kaur (2020). The impact of artificial intelligence on career guidance: A
review. Source Title: International Journal of Educational Management.
[15.] Jingyi Duan, Suhan Wu (2024). Beyond Traditional Pathways: Leveraging Generative AI for
Dynamic Career Planning in Vocational Education. Source Title: International Journal
[16] Dr. Deshpande A.S.1, Dr. Mahajan S.R.2, Dr. Kulkarni S.B.3, Prof Puri S.A. (2024). Impact of
AI on Education: A Review. Source Title: International Journal on advance engineering and
management.
[17.] Ayush Chandrol; Monisha Awasthi; Deepak Sharma; Mani Kansal; Komal Sharma; Ankur
Goel (2024). Career Counselling using AI in the field of IT Industry in Dynamic Environment.
Source Title: IEEE
[18.] HeeWon Hong , YeonKyoung Kim (2024). Applying artificial intelligence in career
education for students with intellectual disabilities: The effects on career self-efficacy and learning
flow. Source Title: Education and Information Technologies
[19.] Celik, I., Dindar, M., Muukkonen, H., & Järvelä, S. (2022). The promises and challenges of
artificial intelligence for teachers: A systematic review of research. Source Title: Technology
Trends
[20.] Gedrimiene, E., Celik, I., Mäkitalo, K., & Muukkonen, H. (2023). Transparency and
trustworthiness in user intentions to follow career recommendations from a learning analytics tool.
Source Title: Journal of Learning Analytics.
[21.] P. Dharani Devi; Sivasankari. S; A. Hemavathi (2024). AI Enhanced career guidance and
aptitude testing for higher education. Source Title: IEEE.
[22.] J. Pio Dinesh, Kevin Luke, Ajo Alen Ajeen & M. Indumathy (2024). AI Guided career advisor
with Integrated AI-Enhanced Decision support. Source Title: Computing Technologies for
Sustainable Development (IRCCTSD).
[23.] Durgeshwary Kolhe, Arshad Bhat (2025). Enhancing career guidance with AI in Vocational
Education. Source Title: IGI Global.

76
[24.] Mrunal Fattepurkar1 , Ankita Shelake1 , Namrata Jagtap1 , Sakshi More1 , Sabiya Tamboli1 ,
K. I. Chouhan2 (2024). Navigate Career Thriving AI Powered Courses Guidance Junction with
Students Reviews. Source Title: International Journal of Scientific Research in Computer Science,
Engineering and Information Technology (IJSCSEIT).
[25.] Salman Shifa, Haider Ali Javaid, Salman Khalid, Fatima Shafiq (2025). How AI Can
Facilitate Continuous Education and Skills Development for Adults throughout Their Careers.
Source Title:
The Critical Review of Social Sciences Studies.
[26.] Rahul Vadisetty; Anand Polamarasetti (2024). AI-Augmented Skill Development Roadmaps:
Tailoring 12 months learning paths for future-ready careers in Education 4.0 and Industry 4.0
Source Title: IEEE.
[27.] Michael Kerres and Katja Buntins (2020). Recommender in AI-enhanced Learning: An
Assessment from the Perspective of Instructional Design. Source Title: Open Education Studies.

[28.] Sister Merceditas O. Ang and Mary Jane D. Aragon (2020). Development of AI-Enhanced
Information Technology Program: Preparing Today’s Students in AI Era. Source Title: EasyChair
Preprint.

[29.] Melissa Peterson (2022). AI-Enhanced Interfaces as Informal Guides. Source Title: Artificial
Intelligence Education in the Context of Work (AALT).

[30.] Aravind Kumar Kalusivalingam, Amit Sharma, Neha Patel, Vikram Singh (2020). Optimizing
Decision-Making with AI-Enhanced Support Systems: Leveraging Reinforcement Learning and
Bayesian Networks. Source Title: Vol. 1 No. 2 (2020): International AL, ML Journal Volume: 1.

[31] D. Wen and D. Zhou (2025). "Predictive Career Guidance and Entrepreneurial Development
for University Students Using Artificial Intelligence and Machine Learning," Journal of
Computational Methods in Sciences and Engineering, vol. 25, no. 2, pp. 123–135, Feb. 2025, doi:
10.1177/14727978251318801.

[32] M. A. Lakshmi, S. S. K., M. Shruthi, N. H. B., and F. Ansari (2024). "AI-Enhanced Career
Guidance System for Personalized Career Pathways," in Proc. Int. Conf. Recent Trends Comput.
Commun. Technol. (ICRCCT), vol. 7, no. 1, pp. 38–44, 2024, doi:
10.59544/odgt6483/icrcct24p7.[33] S. Vignesh, C. Priyanka, H. Manju, and K. Mythili (2021). "An
Intelligent Career Guidance System using Machine Learning," in Proc. ICACCS, pp. 987–990,

77
2021, doi: 10.1109/ICACCS51430.2021.9441978.

[34] S. Westman, J. Kauttonen, A. Klemetti, N. Korhonen, M. Manninen, A. Mononen, S.

Niittymäki, and H. Paananen (2021). "Artificial Intelligence for Career Guidance – Current
Requirements and Prospects for the Future," IAFOR Journal of Education, vol. 9, pp. 43–62, 2021,
doi: 10.22492/ije.9.4.03.

[35] A. Kumar, R. Baksi, and S. Mishra, "Analysis of a Career Prediction Framework Using
Decision Tree (2021)." in Proc. Int. Conf. Innovative Computing and Communication (ICICC), pp.
123–130, Mar. 2021.

[36] H. Al-Dossari, F. Nughaymish, Z. Al-Qahtani, M. Alkahlifah, and A. Alqahtani (2020). "A

Machine Learning Approach to Career Path Choice for Information Technology Graduates,"
Engineering, Technology & Applied Science Research, vol. 10, pp. 6589–6596, 2020, doi:
10.48084/etasr.3821.

[37] R. H. Rangnekar, K. P. Suratwala, S. Krishna, and S. Dhage, "Career Prediction Model Using
Data Mining and Linear Classification," in Proc. 4th Int. Conf. Computing Communication Control
and Automation (ICCUBEA), Pune, India, pp. 1–6, 2018.

[38] L. Zhang, T. Luo, F. Zhang, and Y. Wu, "A Recommendation Model Based on Deep Neural
Network," IEEE Access, vol. 6, pp. 9454–9463, 2018.

[39] M. Kiran, H. Asim, and M. T. Hassan, "Career and Skills Recommendations using Data
Mining Technique: Matching Right People for Right Profession, in Pakistani Context," VFAST
Transactions on Software Engineering, vol. 7, no. 1, pp. 33–41, Dec. 2018.

[40] K. Roy, K. Roopkanth, V. Teja, V. Bhavana, and J. Priyanka, "Student Career Prediction
Using Advanced Machine Learning Techniques," International Journal of Engineering and
Technology (UAE), vol. 7, pp. 26–29, 2018, doi: 10.14419/ijet.v7i2.20.11738.

[41] R. Ade and P. R. Deshmukh, "An Incremental Ensemble of Classifiers as a Technique for

78
Prediction of Student’s Career Choice," in Proc. Int. Conf. Networks and Soft Computing (ICNSC),
pp. 384–387, 2014, doi: 10.1109/CNSC.2014.6906655.

[42] X. Bao, T. Wang, and J. Hu, "Analysis of Individual Career Decision-Making Based on Partial
Least-Squares Regression Model," in Proc. 6th Int. Conf. Fuzzy Systems and Knowledge Discovery
(FSKD), vol. 2, pp. 522–526, 2009, doi: 10.1109/FSKD.2009.192.

[43] N. Gallusser, P. Goetti, F. Becce, F. Vauclair, H. Rüdiger, P. Bize, and S. Cherix,

"Percutaneous image-guided cryoablation of painful bone metastases: A single institution
experience," Orthopaedics & Traumatology: Surgery & Research, 2019, doi:
10.1016/j.otsr.2019.01.001.

[44] M. Uddin and J. Lee, "Predicting Good Fit Students by Correlating Relevant Personality Traits
with Academic/Career Data," in Proc. ASONAM, pp. 968–975, 2016, doi:
10.1109/ASONAM.2016.7752357.

[45] M.-J. Nzengou-Tayo, "Ready to Burst," Caribbean Quarterly, vol. 62, pp. 141–142, 2016, doi:
10.1080/00086495.2016.1157254.

[46] S. Abdulrasoul and M. Puglisi-Weening, "Review of Toxicology in the Middle Ages and
Renaissance," Journal of Natural Products, vol. 80, 2017, doi: 10.1021/acs.jnatprod.7b00604.

[47] A.-S. Guillard, I. Goubet, C. Salles, J. L. Le Quéré, and J.-L. Vendeuvre, "Role of Sodium
Nitrite on Phospholipid Composition of Cooked Cured Ham. Relation to Its Flavor," 1997.

79
PLAGIARISM REPORT

80
81
82
83