VISVESVARAYA TECHNOLOGICAL UNIVERSITY

JNANA SANGAMA, BELGAUM –590 018

Internship Report
On
“INDUSTRY INTERNSHIP”
submitted in partial fulfillment of the requirements for the award of degree of
BACHELOR OF ENGINEERING
in
ELECTRICAL AND ELECTRONICS
Submitted by
PIYUSH
KUMAR
(1BI21EE023)
Internship work carried out at
M1C IT SOLUTIONS Pvt. Ltd.
Bangalore-560091
Under the guidance of
Internal guide External guide
Dr. Ashok Kumar.S Kottersh H M
Assistant Professor HR Manager
Dept. of EEE M1C IT Solutions
BIT, Bangalore Bangalore

DEPARTMENT OF ELECTRICAL AND ELECTRONICS ENGINEERING

BANGALORE INSTITUTE OF TECHNOLOGY
K.R. Road, BANGALORE – 560004
2024-2025
 BANGALORE INSTITUTE OF TECHNOLOGY
K.R. Road, V .V Puram, Bangalore -560004
Phone: 26613237/26615865, Fax: 22426796
www.bit-bangalore.edu.in

DEPARTMENT OF ELECTRICAL AND ELECTRONICS ENGINEERING.

CERTIFICATE

Certified that the Internship work entitled Industry Internship carried out by Mr. Piyush Kumar,
USN:1BI21EE023 a bonafide student of Bangalore Institute Of Technology in partial fulfillment for the
award of Bachelor of Engineering/ Bachelor of Technology in Electrical and Electronics Engineering of
the Visvesvaraya Technological University, Belgaum during the year 2024-2025. It is certified that all
corrections/suggestions indicated for Internal Assessment have been incorporated in the report deposited in the
departmental library. The Internship / Professional practice report has been approved as it satisfies the
academic requirements in respect of Internship / Professional practice work prescribed for the said degree.

Dr. Ashok Kumar.S Dr. P PRAMILA

Assistant Professor Professor & HOD
Dept. of EEE Dept. of EEE

External Viva
Name of the Examiners Signature with date
1.
2.
No 27, Opp East West Institute of Technology, BEL Layout, Bharath Nagar, 1st Phase, Bangalore – 560091
GST No: 29AAMCM6750E1Z5 , CIN: U72900KA2019PTC124201
Email: info@m1citsolutions.com , Ph: 080- 2977 2122/ + 91 84315 12123

INTERNSHIP CERTIFICATION

This is to confirm that Mr. Piyush Kumar has completed the “Artificial Intelligence and

Machine Learning” internship at M1C IT Solutions India Pvt. Ltd., Bangalore-560091,

from 1st February 2025 to 15th May 2025.

Thanks & Regards

M1C IT Solutions India Pvt. Ltd, Bangalore
Mob- 8431512123/ 9538546229
 ACKNOWLEDGMENT

I deeply indebted to guide Dr Ashok Kumar. S, Assistant Professor, Department

of Electrical & Electronics Engineering, Bangalore Institute of Technology, for
his immense and valuable support, guidance and encouragement throughout the
course of Internship. His enthusiasm and thirst for knowledge has always
inspired us to try harder. Special regards are conveyed to him for sparing
precious time.

I extend my heartfelt thanks to Internship coordinators NANDINI N, Assistant

Professor, Dr. Ashok Kumar.S, Assistant Professor for constant revitalization,
motivation and recommendations in preparation of presentation, documentation
and continuous process of Internship.

It is my duty to extend my gratitude to the Internship coordinators, H. Suresh,

Assistant Professor, for her valuable suggestions, revisions and immense
support in maintaining quality of Internship.

I would also extend my gratitude to Dr. P. PRAMILA Professor & Head,

Department of Electrical and Electronics Engineering, for allowing and aiding
in the compilation of the Internship.

I would like to thank Dr. M. U. ASWATH, Principal, Bangalore institute of

technology for providing the congenial ambience to work in the institution. I
was pleased to express our heart full thanks to all the teaching and technical
faculty of dept. of EEE, BIT. Bangalore who gave us moral support and
encouragement during the Internship.

Name of the student USN

Piyush Kumar 1BI21EE023

i
 BANGALORE INSTITUTE OF TECHNOLOGY

VISION
Establish and develop the Institute as the Centre of higher learning, ever abreast with expanding
horizon of knowledge in the field of Engineering and Technology with entrepreneurial thinking,
leadership excellence for life-long success and solve societal problems.

MISSION
 Provide high quality education in the Engineering disciplines from the undergraduate
through doctoral levels with creative academic and professional programs.
 Develop the Institute as a leader in Science, Engineering, Technology, Management and
Research and apply knowledge for the benefit of society.
 Establish mutual beneficial partnerships with Industry, Alumni, Local, State and Central
Governments by Public Service Assistance and Collaborative Research.
 Inculcate personality development through sports, cultural and extracurricular activities
and engage in social, economic and professional challenges.

Program Educational Objectives (PEOs)

 Uplift the students through Information Technology Education.

 Provide exposure to emerging technologies and train them to Employable in multi-

disciplinary industries.
 Motivate them to become good professional Engineers and Entrepreneur.

 Inspire them to prepare for Higher Learning and Research.

Program Specific Outcomes (PSOs)

 To provide our graduates with Core Competence in Information Processing and
Management.
 To provide our graduates with Higher Learning in Computing Skills.

ii
 ELECTRICAL AND ELECTRONICS ENGINEERING

VISION
To produce competent Engineers to excel in the field of Electrical and Electronics Engineering by
adopting strong teaching and research environment.

MISSION
 To prepare graduates for life-long learning and leadership roles in their chosen fields

 To prepare students to provide technically sound, feasible and socially acceptable

solutions to the real life problems
 To develop critical thinking, social and ethical responsibilities, team work and
communication skills in graduate students
 To start post graduate programs and enhance the capabilities of research centre through
industry institute interaction
 To motivate students to pursue higher studies and promote entrepreneurship

Program Educational Objectives (PEO's)

 Graduate of Electrical and Electronics engineering will excel as professionals with
acquired knowledge in mathematics, science and engineering principles.
 Graduate of Electrical and Electronics engineering will possess the ability to identify and
analyze real life problems and provide solutions that are technically sound, economically
feasible and socially acceptable
 Graduate of Electrical and Electronics Engineering will exhibit professionalism, ethical
attitude, communication skills, team work and adapt to current trends by engaging in life-
long learning
 Graduate of Electrical and Electronics Engineering will exhibit interest in higher studies
and research

Program Outcomes
 Engineering knowledge: Apply the knowledge of mathematics, science, engineering
fundamentals, and an engineering specialization to the solution of complex engineering
problems.

iii
 Problem analysis: Identify, formulate, review research literature, and analyze complex
engineering problems reaching substantiated conclusions using first principles of
mathematics, natural sciences, and engineering sciences.
 Design/development of solutions: Design solutions for complex engineering problems
and design system components or processes that meet the specified needs with
appropriate consideration for the public health and safety, and the cultural, societal, and
environmental considerations.
 Conduct investigations of complex problems: Use research-based knowledge and
research methods including design of experiments, analysis and interpretation of data,
and synthesis of the information to provide valid conclusions.
 Modern tool usage: Create, select, and apply appropriate techniques, resources, and
modern engineering and IT tools including prediction and modelling to complex
engineering activities with an understanding of the limitations.
 The engineer and society: Apply reasoning informed by the contextual knowledge to
assess societal, health, safety, legal and cultural issues and the consequent responsibilities
relevant to the professional engineering practice.
 Environment and sustainability: Understand the impact of the professional engineering
solutions in societal and environmental contexts, and demonstrate the knowledge of, and
need for sustainable development.
 Ethics: Apply ethical principles and commit to professional ethics and responsibilities
and norms of the engineering practice.
 Individual and team work: Function effectively as an individual, and as a member or
leader in diverse teams, and in multidisciplinary settings.
 Communication: Communicate effectively on complex engineering activities with the
engineering community and with society at large, such as, being able to comprehend and
write effective reports and design documentation, make effective presentations, and give
and receive clear instructions.
 Project management and finance: Demonstrate knowledge and understanding of the
engineering and management principles and apply these to one’s own work, as a member
and leader in a team, to manage projects and in multidisciplinary environments.
 Life-long learning: Recognize the need for, and have the preparation and ability to
engage in independent and life-long learning in the broadest context of technological
change.

Program Specific Outcomes

 Model, estimate, simulate and analyze the performance of power system operation,
control and their protection mechanisms.
 Design electrical machines to the given specifications, analyze and test their performance.

 Design, develop and analyze electrical and electronic systems for applications to power
and other domains.

iv
 BANGALORE INSTITUTE OF TECHNOLOGY
(Affiliated to VTU, Belagavi, Recognized by AICTE, New Delhi)
Department of Electrical & Electronics Engineering
K R Road, V V Pura, Bengaluru – 560004
Phone – 9945128466 Fax: 080-22426796
Website: www.bit-bangalore.edu.in, Email: eeebit2020@gmail.com

INT21INT82 Industry Internship

Academic Year: 2024-25

Course Outcomes:
CO-1: Apply and develop knowledge in the field of engineering and other discipline
through independent learning and collaborative study.
CO-2: Identify, understand and discuss current and real time issues.
CO-3: Improve verbal communication skills.
CO-4: Explore and appreciation of self in relation to its diverse social and academic
contexts.
CO-5: Apply principles of ethics and respect in interaction with others.

Project guide evaluation report:

Allotment of marks based on CO’s:

Maximum
Cos CO-1 CO-2 CO-3 CO-4 CO-5
Marks

Marks
10 10 10 10 10 50
division

Marks
secured

Presentation evaluation report:

The final presentation is evaluated by 3 juries’ considering the following parameters.

1. Slide preparation and topic selection – 10 marks
2. Presentation skills– 30 marks.
3. Questionnaire’s (Viva-voce) – 10 marks.

IQAC Coordinator Signature of internship

Coordinator

v
 CO-PO-PSO mapping:

CO PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3

CO1 3 3 3 2 2 2 2 2 2 2 2 3 2 2
CO2 3 3 2 2 3 2 2
CO3 3 2 3 2 2
CO4 3 2 2 2 2 2
CO5 3 2 2 2 2
INT21 3 3 3 2 2 3 2 2 2 3 3 2 3 3 3
INT82

CO-1: Apply and develop knowledge in the field of engineering and other discipline
through independent learning and collaborative study.
CO-2: Identify, understand and discuss current and real time
issues. CO-3: Improve verbal communication skills.
CO-4: Explore and appreciation of self in relation to its diverse social and academic
contexts.
CO-5: Apply principles of ethics and respect in interaction with others.

vi
 TABLE OF CONTENTS

Acknowledgment i

Institute Vision/Mission ii

Department Vision/Mission iii

Course outcome of Internship, CO-PO mapping table v

Contents vii

List of figures ix

List of tables x

1. Profile of the Organization 1

1.1 Organizational Structure 1

1.1.1 Organizational Structure of M1C IT Solutions 1

1.1.2 Products 2

1.1.3 Services 4

1.1.4 Business Partner 5

1.1.5 Financials 6

1.1.6 Manpower 6

1.1.7 Societal Concerns 7

1.1.8 Professional Practices 7

2. Activities of the Department 8

2.1 Industry/Company 9

3. Tasks performed during 15 Weeks Period 10

3.1 Weeks 1–2 Project Understanding and Requirement Analysis 10

vii
 3.2 Weeks 3–4: Data Collection and Feature Identification 10

3.3 Weeks 5–6: Data Preprocessing and Exploratory Analysis 11

3.4 Weeks 7–8: Model Building for CGPA and SGPA Prediction 12

3.5 Weeks 9–10: Model Building for Backlog Classification 13

3.6 Weeks 11–12: Web Interface Development and Integration 14

3.7 Weeks 13–14: Testing and Documentation 15

3.8 Week 15: Final Presentation and Submission 15

3.8.1 Dataset snapshot 16

3.8.2 Statistical Summary of the Dataset 16

3.8.3 Interpretation of Results 16

3.8.4 Model Evaluation Results 17

4. Reflections 18

4.1 Technical Skills Acquired 19

4.2 Soft Skills Acquired 21

CONCLUSION 22

REFERENCE & ANNEXURE 23

viii
 List of Figures

Fig. No. Figure Description Page No.

3.1 Setting up Project Folder 10
3.2 Sample Student Dataset 11
3.3 System Flow Diagram 12
3.4 Data Flow Diagram 13
3.5 Feature Importance Bar Plot 14
3.6 Comparative Visualization of Model Accuracy 14
3.7 Data Set Snapshot 16
3.8 Data Set Statistics 16
8.3 Feature Importance 35

ix
 List of Tables

Table Page
Description of the Table
No. No.
3.1 Algorithm Used 13
3.2 Unit Testing 15

x
 Industry Internship

CHAPTER - I

PROFILE OF THE ORGANIZATION

1.1 Organizational Structure

M1C IT Solutions is a small to mid-sized IT company, so its organizational structure is likely to
be flat or moderately hierarchical, which allows for flexibility, innovation, and faster decision-
making.

1.1.1 Organizational Structure of M1C IT Solutions

1. Managing Director / CEO

 Overall leadership and strategic direction of the company.

 Oversees major business decisions, partnerships, and financial planning.

2. Chief Technology Officer (CTO)

 Heads the technical department.

 Leads software architecture, R&D, and ensures adoption of the latest technologies.

3. Project Manager

 Coordinates projects between development teams and clients.

 Manages deadlines, deliverables, and resource allocation.

4. Development Team

 Full Stack Developers

o Handle backend (Node.js, MongoDB, PHP) and frontend (React, AngularJS)

development.

 AI/ML Engineers

o Work on machine learning models, NLP, and chatbot integration.

 UI/UX Designers

DEPT. OF EEE, 2024-2025 Page | 01

BIT
 Industry Internship

o Focus on creating intuitive and responsive interfaces.

5. Quality Assurance (QA) Team

 Conducts testing to ensure software quality, usability, and bug-free delivery.

6. Business Development & Marketing Team

 Works on client acquisition, branding, and marketing strategies.

 Handles communication, social media, and promotional campaigns.

7. Human Resources (HR)

 Recruitment, employee engagement, training, and company policy enforcement.

8. Support & Maintenance Team

 Provides technical support to clients.

 Ensures system uptime and handles bug fixes or performance issues.

1.1.2 Products

Products Offered by M1C IT Solutions

1. Learning Management System (LMS)

o A robust platform designed to facilitate digital learning.

o Offers course creation, student progress tracking, assessments, and certifications.

o Ideal for schools, colleges, coaching centers, and corporate training.

o Includes role-based access for admins, instructors, and learners.

2. School and College Management System

o Comprehensive ERP solution tailored for educational institutions.

o Modules include student enrollment, fee management, attendance, timetable

scheduling, staff payroll, and exam results.

o Helps automate and digitize administrative tasks, reducing paperwork.

DEPT. OF EEE, 2024-2025 Page | 02

BIT
 Industry Internship

3. Quiz and Assessment System

o Interactive platform for creating and conducting quizzes and exams.

o Supports multiple question types: MCQs, subjective, fill-in-the-blanks, etc.

o Provides real-time scoring, analytics, and performance tracking.

4. AI Recommendation Engine

o Personalized content or product suggestion system based on user behavior and data.

o Can be integrated into e-learning platforms, shopping apps, or content portals.

o Improves user engagement by offering smart, data-driven suggestions.

5. Chatbots and NLP-Based Assistants

o Conversational agents built using Natural Language Processing (NLP) for

automation and customer support.

o Customizable for industries like education, retail, and healthcare.

o Can handle FAQs, guide users, and collect feedback efficiently.

6. Analytics & Reporting Tools

o Visual dashboards and detailed reports for business intelligence.

o Enables stakeholders to make informed decisions based on data trends.

o Integrated into other systems like LMS and ERP for real-time performance
analysis.

7. Custom Web and Mobile Applications

o Full-stack development services for tailor-made apps.

o Tech stack includes Node.js, MongoDB, PHP, React, Angular, and more.

o Offers both frontend and backend solutions for diverse industries.

8. Data Privacy and Compliance Tools

o Ensures secure data handling in line with legal and ethical standards.

o Useful for educational and enterprise platforms dealing with sensitive user data.

DEPT. OF EEE, 2024-2025 Page | 03

BIT
 Industry Internship

1.1.3 Services

Services Offered by M1C IT Solutions

1. Full-Stack Development

o End-to-end web and mobile application development.

o Uses technologies like PHP (CodeIgniter), Node.js, MongoDB, AngularJS,

React, and JavaScript.

o Includes both frontend (user interface) and backend (server-side) development.

2. Artificial Intelligence (AI) & Machine Learning (ML) Solutions

o Development of AI models to solve real-world problems.

o Applications include recommendation systems, predictive analytics, and

intelligent automation.

3. Natural Language Processing (NLP)

o Building systems that understand and interpret human language.

o Used in chatbots, sentiment analysis, and voice/text-based interfaces.

4. Chatbot Development

o AI-powered conversational agents for automating customer support, FAQs, and

onboarding.

o Custom-built for education, e-commerce, and enterprise platforms.

5. Data Analytics & Business Intelligence

o Extracting insights from data to support decision-making.

o Includes data visualization dashboards, trend analysis, and reporting systems.

6. UI/UX Design

o Designing user-centric, responsive, and interactive interfaces.

o Focuses on improving usability, accessibility, and overall user experience.

DEPT. OF EEE, 2024-2025 Page | 04

BIT
 Industry Internship

7. Custom Software Development

o Tailor-made solutions for unique business requirements.

o Covers ERP systems, learning platforms, e-commerce apps, and more.

8. Cloud-Based Solutions

o Scalable, secure cloud integration for web applications.

o Supports deployment, data storage, and remote access.

9. Maintenance & Support

o Post-deployment support and bug fixing.

o Regular updates, performance optimization, and system upgrades.

10. Digital Transformation Consulting

 Helping organizations modernize their processes with digital tools and automation.

 Includes assessment, planning, and implementation of digital strategies.

1.1.4 Business Partner

As of now, M1C IT Solutions India Pvt. Ltd. does not publicly list specific business partners on its
official website or in available public records. However, given the company's focus on
educational software development and IT services, it is common for such organizations to
collaborate with various entities to enhance their offerings. These collaborations might include:

 Educational Institutions: Partnering with schools, colleges, and universities to tailor

software solutions that meet specific academic needs.

 Technology Providers: Collaborating with tech companies to integrate advanced

features like AI, machine learning, and cloud services into their products.

 Consulting Firms: Working with business consultants to understand market demands

and customize solutions accordingly.

 Government and Non-Profit Organizations: Engaging with governmental bodies or

NGOs for projects aimed at educational development and digital literacy.

DEPT. OF EEE, 2024-2025 Page | 05

BIT
 Industry Internship

1.1.5 Financials

Financial Overview of M1C IT Solutions

 Company Details

 Incorporation Date: May 9, 2019

 Corporate Identification Number (CIN): U72900KA2019PTC124201

 Registered Office: 27, Anjana Nagar, Opposite to East West College Road,
Bangalore, Karnataka 560091, India

 Authorized Share Capital: ₹3,00,000

 Paid-up Share Capital: ₹1,00,000

 Financial Performance (As of March 31, 2023)

 Revenue Growth: 0% increase compared to the previous year

 Profit Growth: 96.77% increase in profit

 Net Worth Change: 2.53% decrease

 EBITDA Growth: 97.32% increase

Note: Specific figures for total revenue, profit, and assets are not publicly disclosed.

 Compliance and Filings

 Last Annual General Meeting (AGM): August 30, 2023

 Last Filed Balance Sheet: March 31, 2023

1.1.6 Manpower

The M1C IT Solutions India Pvt. Ltd. is a small to mid-sized company. The company's has a team of
15 members.

The organizational structure likely includes roles such as:

 Managing Director / CEO: Oversees overall leadership and strategic direction.

 Chief Technology Officer (CTO): Leads the technical department and software
architecture.

DEPT. OF EEE, 2024-2025 Page | 06

BIT
 Industry Internship

 Project Manager: Coordinates projects between development teams and clients.

 Development Team: Comprising full-stack developers, AI/ML engineers, and UI/UX

designers.

 Quality Assurance (QA) Team: Ensures software quality and usability.

 Business Development & Marketing Team: Handles client acquisition and marketing
strategies.

 Human Resources (HR): Manages recruitment and employee engagement.

 Support & Maintenance Team: Provides technical support and system maintenance.

1.1.7 Societal Concerns

 Enhancing Educational Access: By developing Learning Management Systems (LMS)

and school/college management software, M1C IT Solutions facilitates digital learning,
potentially improving educational access and quality.
 Promoting Digital Literacy: Their software solutions may aid in increasing digital
literacy among students and educators, contributing to skill development in the
community.
 Supporting Educational Institutions: Collaborations with schools and colleges to
implement their software solutions could assist these institutions in modernizing their
operations and enhancing learning experiences.

1.1.8 Professional Practices

 Client-Centric Approach: Prioritizing client requirements and delivering customized

software solutions to meet specific educational needs.
 Quality Assurance: Implementing rigorous testing and quality control measures to
ensure the reliability and effectiveness of their software products.
 Data Security and Privacy: Emphasizing the protection of sensitive educational data
through secure software design and compliance with relevant data protection regulations.
 Continuous Learning and Innovation: Encouraging ongoing professional development
and staying abreast of emerging technologies to enhance their service offerings.

DEPT. OF EEE, 2024-2025 Page | 07

BIT
 Industry Internship

CHAPTER - II

ACTIVITIES OF THE DEPARTMENT

2.1 Industry/Company
1. Software Development Department

 Designing, coding, testing, and deploying web and mobile applications.

 Working on both frontend (UI/UX) and backend (database, APIs).

 Implementing technologies like Node.js, MongoDB, PHP, React, Angular.

 Collaborating on AI/ML models and chatbot development.

2. Artificial Intelligence & Machine Learning Department

 Developing intelligent solutions like recommendation engines and NLP chatbots.

 Training and testing machine learning models.

 Integrating AI features into educational and business applications.

3. UI/UX Design Department

 Creating user-friendly and responsive interface designs.

 Conducting user research to enhance usability.

 Prototyping and testing UI elements.

4. Quality Assurance (QA) Department

 Performing manual and automated testing of software.

 Ensuring bug-free releases and functionality as per client requirements.

 Writing test cases and maintaining documentation for test results.

5. Project Management Department

 Planning, scheduling, and tracking project milestones.

 Allocating resources and coordinating between teams.

DEPT. OF EEE, 2024-2025 Page | 08

BIT
 Industry Internship

 Communicating with clients and ensuring timely delivery.

6. Business Development and Marketing Department

 Identifying new business opportunities and client partnerships.

 Promoting products and services through digital channels.

 Preparing proposals and presentations for potential clients.

7. Human Resources (HR) Department

 Recruiting skilled professionals and onboarding interns.

 Managing employee relations, payroll, and compliance.

 Organizing training sessions and professional development activities.

8. Technical Support & Maintenance Department

 Offering post-deployment support and system monitoring.

 Resolving client issues and ensuring smooth operation of software.

 Updating and patching applications as needed.

DEPT. OF EEE, 2024-2025 Page | 09

BIT
 Industry Internship

CHAPTER – III

TASKS PERFORMED DURING 15 WEEKS PERIOD

3.1 Weeks 1–2: Project Understanding and Requirement Analysis

At the beginning of the internship, I was introduced to the problem of predicting academic outcomes
for students, specifically CGPA (Cumulative Grade Point Average), SGPA (Semester Grade
Point Average), and the likelihood of having backlogs. I held discussions with my mentor to
understand how such a model could be useful for educational institutions in identifying students
at risk. I also studied how prediction systems are structured in real-world applications. During
these weeks, I finalized the project scope and identified the required data attributes, such as
semester-wise SGPA, attendance, assignment scores, internal exam marks, and past backlog
records. This phase set a clear foundation for the technical work ahead.

Fig : 3.1 Setting up Project Folder

3.2 Weeks 3–4: Data Collection and Feature Identification

Once the project scope was defined, I began collecting datasets. The dataset included records of
students with various academic metrics such as:
 SGPA for each semester
 Class attendance
 Assignment and quiz scores
 Mid-semester exam marks
 Previous backlog count

DEPT. OF EEE, 2024-2025 Page | 10

BIT
 Industry Internship

I studied each feature's relevance in predicting CGPA and SGPA through correlation matrices and
academic research. After thorough analysis, I shortlisted the most relevant input features that
would contribute significantly to building accurate prediction models. This phase also involved
cleaning the raw data and making it suitable for preprocessing.

Fig : 3.2 Sample Student Dataset

3.3 Weeks 5–6: Data Preprocessing and Exploratory Analysis

With a clean dataset in hand, I started preprocessing the data to make it ready for machine learning
models. This included:
 Handling missing or inconsistent entries

 Label encoding categorical variables like department and year

 Normalizing and scaling continuous features to bring them on a common scale

I also conducted Exploratory Data Analysis (EDA) to extract insights and visual patterns from the
dataset. I used visualizations such as histograms, boxplots, heatmaps, and scatter plots to observe

DEPT. OF EEE, 2024-2025 Page | 11

BIT
 Industry Internship

how variables like attendance and SGPA impacted CGPA and backlog occurrence. These
insights helped in understanding which features had the most influence on academic
performance.

3.4 Weeks 7–8: Model Building for CGPA and SGPA Prediction

I focused on building regression models to predict both CGPA and SGPA values based on the
available student data. I implemented and compared several algorithms, including:
 Linear Regression: for its simplicity and interpretability
 Decision Tree Regressor: for handling non-linear data
 Random Forest Regressor: for better accuracy and robustness
I used an 80/20 train-test split and evaluated the models using metrics like R² score, Mean
Squared Error (MSE), and Mean Absolute Error (MAE). The Random Forest Regressor
consistently gave the best results for both CGPA and SGPA prediction, showing high accuracy
and low error rates.

Fig : 3.3 System Flow Diagram

DEPT. OF EEE, 2024-2025 Page | 12

BIT
 Industry Internship

Fig : 3.4 Data Flow Diagram

3.5 Weeks 9–10: Model Building for Backlog Classification

While CGPA and SGPA were regression problems, backlog prediction was treated as a binary
classification task (i.e., backlog or no backlog). I used various classification algorithms such as:
 Logistic Regression
 Random Forest Classifier
 Support Vector Machine (SVM)
I evaluated these models using accuracy, precision, recall, and F1-score to measure how well
they identified students likely to have backlogs. Random Forest and SVM outperformed others,
offering accurate predictions even on unseen data. This helped in successfully separating
students who were "at risk" from those in the "safe" category.

Task Algorithms Used

Regression Linear Regression, Decision Tree Regressor
Classification Random Forest Classifier, Logistic Regression

Table : 3.1 Algorithms Used

DEPT. OF EEE, 2024-2025 Page | 13

BIT
 Industry Internship

Fig : 3.5 Feature Importance Bar Plot

Fig : 3.6 Comparative Visualization of Model Accuracy

3.6 Weeks 11–12: Web Interface Development and Integration

Once the models were finalized, I worked on building a user-friendly web interface using Flask.
This included:
 Creating HTML forms for inputting student data
 Designing the backend in Python to process the input and pass it to the trained models
 Displaying predicted CGPA, SGPA, and backlog status in a readable format

DEPT. OF EEE, 2024-2025 Page | 14

BIT
 Industry Internship

This interface allowed real-time predictions based on custom user input and acted as a working
prototype for educational institutions to use.

3.7 Weeks 13–14: Testing and Documentation

In this phase, I focused on:

 Testing the models and web interface for accuracy, usability, and stability
 Creating test cases and running multiple inputs to validate model behavior
 Preparing complete technical documentation including:
o Data flow diagrams
o Model architecture
o Screenshots of the UI
o Code annotations
o Results and evaluation metrics
Additionally, I documented limitations and possible improvements such as adding more academic
behavior metrics (e.g., time spent studying, course difficulty) and expanding the dataset size for
better generalization.

Function Tested Test Description Result

Load Dataset Check if CSV loads properly Pass
Fill Missing Values Ensure no NaN exists after preprocessing Pass
Model Training Check if .fit() completes without error Pass
Prediction Function Input sample data and get output Pass
Output Display Check if result is correctly shown Pass

Table : 3.2 Unit Testing

3.8 Week 15: Final Presentation and Submission

In the final week, I presented the project to my mentor and the technical team at M1C IT Solutions. I
explained:
 The objectives and scope of the project
 The methodology followed from data preprocessing to deployment
 Performance metrics of the final models

DEPT. OF EEE, 2024-2025 Page | 15

BIT
 Industry Internship

 A live demo of the web interface showing predictions

I submitted all project materials including the codebase, dataset, UI files, and the final project report.
The project was appreciated for its relevance, accuracy, and practical usability in academic
institutions.
3.8.1 Dataset Snapshot
A preview of the dataset is shown below, containing a few initial records of the dataset used in the
study:

Fig : 3.7 Data Set Snapshot

This table displays the core attributes considered in the project—namely academic background,
engagement level (via attendance), performance deficiencies (via backlogs), practical exposure
(via internship), and final performance (CGPA).
3.8.2 Statistical Summary of the Dataset
The following table summarizes the descriptive statistics of the dataset:

Fig : 3.8 Dataset Statistics

3.8.3 Interpretation of Results
Based on the above descriptive analysis, the following interpretations can be made:
 Academic Performance Trends:
o The average previous semester CGPA is 7.74, and the average next semester
CGPA is 8.37, showing a general improvement.
o The CGPA range (6.0 to 9.5) reflects a diverse set of students from lower to high
performers.
 Attendance Factor:
o The average attendance is 79.27%, with most students maintaining above 70%.
High attendance may correlate positively with CGPA improvement.

DEPT. OF EEE, 2024-2025 Page | 16

BIT
 Industry Internship

 Backlogs:
o The majority of students had 1–3 backlogs in the previous semester, with an
average of 1.53. Managing or reducing backlogs appears crucial to improving
academic outcomes.
 Internship Experience:
o About 47% of students had internship experience, which is hypothesized to
contribute positively to academic performance through applied learning.
 Target Variable – Next Semester CGPA:
o The distribution of next semester CGPA shows academic growth for many
students and allows the prediction model to learn trends effectively.

3.8.4 Model Evaluation Results

To predict student academic performance (SGPA, CGPA, or Backlogs), we implemented and
evaluated multiple regression algorithms. Each model was assessed using three evaluation metrics:
 MSE (Mean Squared Error): Measures the average of the squares of the errors.
 MAE (Mean Absolute Error): Measures the average of the absolute errors.
 R² Score (Coefficient of Determination): Represents the proportion of the variance in
the dependent variable that is predictable from the independent variables.
Below is a summary and analysis of each model:
Linear Regression
 MSE: 0.2037
 MAE: 0.3639
 R² Score: 0.7700
Explanation:
Linear Regression performed well, achieving an R² score of 0.77, meaning the model can explain
77% of the variance in academic performance using the input features. The low error values
(MSE and MAE) indicate a good fit to the data. This model serves as a strong and interpretable
baseline.

Ridge Regression
 MSE: 0.2035
 MAE: 0.3638
 R² Score: 0.7702
Explanation:
Ridge Regression is a regularized version of Linear Regression. It achieved a slightly better R²

DEPT. OF EEE, 2024-2025 Page | 17

BIT
 Industry Internship

score (0.7702) than basic linear regression, with almost identical error values. This suggests that
regularization helped reduce potential overfitting while maintaining high accuracy.

Random Forest Regression

 MSE: 0.2616
 MAE: 0.3901
 R² Score: 0.7046
Explanation:
Random Forest performed slightly worse than the linear models. With an R² score of 0.70, it still
explained a good portion of the data variance but had higher errors. The model likely overfits or
underperforms due to either the small dataset or lack of deep non-linear relationships in the data.

Support Vector Regression (SVR)

 MSE: 0.2202
 MAE: 0.3642
 R² Score: 0.7513
Explanation:
SVR gave a balanced performance, better than Random Forest but slightly lower than Linear and
Ridge Regression. It maintained moderate error values and had a good ability to generalize with
an R² of 0.75.

DEPT. OF EEE, 2024-2025 Page | 18

BIT
 Industry Internship

CHAPTER - IV

REFLECTIONS
During my internship at M1C IT Solutions, I worked on the project titled “Performance
Prediction of CGPA, SGPA, and Backlogs” as a AI Intern. Over the 15-week period, I was
able to gain not only in-depth technical knowledge but also develop essential soft skills required
in a professional environment. This chapter reflects on the wide range of skills I acquired and
how the experience helped shape my academic and career development.

4.1 Technical Skills Acquired

1. Data Collection and Preprocessing
 I learned how to identify the right sources of data and understand the structure of student
academic records.
 Collected real or simulated data on student performance parameters such as semester-
wise SGPA, attendance, assignments, quiz scores, and prior backlogs.
 Cleaned the dataset by handling null or missing values, removed duplicates, and
standardized entries.
 Used techniques such as label encoding, one-hot encoding, and feature scaling (e.g., Min-
Max and StandardScaler) to prepare the data for machine learning models.
2. Exploratory Data Analysis (EDA)
 Developed skills in understanding the behavior of data using matplotlib, seaborn, and
pandas.
 Generated visual representations like heatmaps, histograms, boxplots, and correlation
matrices to find relationships between academic variables.
 Discovered insights such as the influence of attendance and SGPA trends on CGPA
outcomes and backlog likelihood.
3. Machine Learning Model Building
 Gained hands-on experience with supervised learning methods:
o For regression: Linear Regression, Decision Tree Regressor, Random Forest
Regressor
o For classification: Logistic Regression, Support Vector Machine (SVM), Random
Forest Classifier
 Learned how to split data into training and testing sets, apply cross-validation, and avoid
overfitting.

DEPT. OF EEE, 2024-2025 Page | 19

BIT
 Industry Internship

 Gained knowledge of key model evaluation metrics:

o For Regression: R² Score, Mean Absolute Error (MAE), Mean Squared Error
(MSE)
o For Classification: Accuracy, Precision, Recall, F1-score, Confusion Matrix
 Improved models iteratively by hyperparameter tuning and performance comparison.
4. Flask Web Application Development
 Designed and developed a Flask-based web application that allowed users to input
student academic details.
 Integrated the trained machine learning models with a frontend form to deliver
predictions in real-time.
 Implemented form validation, result display, and user interface responsiveness using
HTML, CSS, and Python.
 Learned how to deploy machine learning models in a web environment for practical, real-
world usage.
5. Project Documentation and Version Control
 Maintained proper version control of code using Git and GitHub, allowing for easy
tracking of changes and collaborative work.
 Documented the entire process including:
o Problem statement
o Data understanding
o Preprocessing steps
o Model selection and results
o Visualizations and screenshots
 Created a final report and presentation that explained the technical workflow, model
performance, and system interface.

DEPT. OF EEE, 2024-2025 Page | 20

BIT
 Industry Internship

4.2 Soft Skills Acquired

1. Analytical Thinking and Problem Solving
 Developed the ability to think critically about data and identify what features affect
student performance.
 Solved complex problems such as detecting multicollinearity, improving low-performing
models, and identifying overfitting in classification.
2. Communication and Team Collaboration
 Regularly interacted with the company mentor and technical team members to discuss
progress and get guidance.
 Improved technical communication skills by explaining model choices and prediction
outcomes to both technical and non-technical audiences.
 Learned to give and receive constructive feedback in team meetings.
3. Time Management and Planning
 Managed project timelines effectively by breaking the project into phases: data
collection, modeling, interface development, testing, and final review.
 Met all deliverables within the expected timelines through weekly and bi-weekly targets.
 Balanced project workload with self-paced learning to acquire new tools and concepts
quickly.
4. Adaptability and Continuous Learning
 Faced challenges while understanding real-world data complexity, and adapted by
learning new libraries (e.g., Scikit-learn, Flask) and exploring documentation.
 Picked up concepts like web deployment, evaluation metrics, and frontend-backend
integration during the course of the internship.
5. Professionalism and Responsibility
 Gained exposure to the workings of a real IT company environment.
 Maintained professional decorum in meetings, email communication, and project reviews.
 Took complete ownership of the project—from problem definition to delivery and
demonstration.

DEPT. OF EEE, 2024-2025 Page | 21

BIT
 Industry Internship

CONCLUSION
My internship at M1C IT Solutions provided me with a meaningful opportunity to bridge the gap
between academic learning and real-world applications. Working on the project titled
“Performance Prediction of CGPA, SGPA, and Backlogs”, I was able to apply my
knowledge of machine learning, data analytics, and software development in a practical and
impactful manner.

Through this project, I understood the critical importance of data in decision-making and how
predictive models can be used to identify students at academic risk. I built and evaluated multiple
machine learning models to predict academic performance and backlog likelihood, gaining
strong technical proficiency in data preprocessing, regression/classification algorithms, and
model deployment. The web interface I developed made the system accessible and usable by
non- technical users, emphasizing the need for simplicity in design.

My role also involved active collaboration with team members, consistent reporting to mentors, and
adapting to industry expectations—helping me enhance my communication, teamwork, and time
management skills. The structured environment at M1C IT Solutions, combined with their
guidance and support, made it possible to complete the project successfully within the stipulated
time.

Overall, this internship not only deepened my technical capabilities but also gave me insight into
how software solutions are designed, developed, and delivered in a professional IT environment.
It was a valuable stepping stone in my career, preparing me for future challenges in the field of
data science and software engineering.

DEPT. OF EEE, 2024-2025 Page | 22

BIT
 Industry Internship

REFERENCES

[1] Bhushan, M., Vyas, S., Mall, S., & Negi, A. (2023). A comparative study of machine
learning and deep learning algorithms for predicting student’s academic performance.
International Journal of System Assurance Engineering and Management, 14, 2674–2683.

[2] Baashar, Y., Hamed, Y., Alkawsi, G., Capretz, L. F., Alhussian, H., & Alwadain, A. (2022).
Evaluation of postgraduate academic performance using artificial intelligence models.
Alexandria Engineering Journal, 61(11), 9867–9878.

[3] Adekitan, A. I., & Salau, O. (2019). The impact of engineering students’ performance in the
first three years on their graduation result using educational data mining. Heliyon, 5(2), e01250.

[4] Junejo, K. N. (2016). Grade prediction using supervised machine learning techniques. In
Proceedings of the 4th Global Summit on Education (pp. 14–15). Kuala Lumpur.

[5] Lau, E. T., Sun, L., & Yang, Q. (2019). Modelling, prediction and classification of student
academic performance using artificial neural networks. SN Applied Sciences, 1(9), 1–10.

[6] Samsudin, N. A. M., Shaharudin, S. M., Sulaiman, N. A. F., Smail, S. I., Mohamed, N. S., &
Husin, N. H. M. (2022). Prediction of student’s academic performance during online learning
based on regression in support vector machine. International Journal of Information and
Education Technology, 12(12), 1431–1435.

[7] Saifuzzaman, M., Parvin, M., Jahan, I., Moon, N. N., & Nur, F. N. (2021). Machine learning
approach to predict SGPA and CGPA. In 2021 International Conference on Artificial
Intelligence and Computer Science Technology (pp. 211–216). IEEE.

[8] Rai, S., Shastry, K. A., Pratap, S., Kishore, S., Mishra, P., & Sanjay, H. A. (2021). Machine
learning approach for student academic performance prediction. In Advances in Intelligent
Systems and Computing (Vol. 1176, pp. 611–618). Springer.

[9] Sharma, D., & Aggarwal, D. (2021). A predictive approach to academic performance
analysis of students based on parental influence. In Advances in Intelligent Systems and
Computing (Vol. 1165, pp. 75–84). Springer.

[10] Oladokun, V. O., Adebanjo, A. T., & Charles-Owaba, O. E. (2008). Predicting students’
academic performance using artificial neural network: A case study of an engineering course.
The Pacific Journal of Science and Technology, 9(1), 72–79.

DEPT. OF EEE, 2024-2025 Page | 23

BIT