A

Seminar Report
On

“RECOMMENDATION SYSTEMS:
BUILDING PERSONALIZED EXPERIENCE”
Submitted for the partial fulfillment of requirement for the degree of

BACHELOR OF ENGINEERING
Computer and Science Engineering

Submitted By
Mr. Sumit D. Patil

Under the Guidance of

Prof. V. G. Telharkar

Department of Computer Science and Engineering

Siddhivinayak Technical Campus, Shegaon.
Sant Gadge Baba Amravati University, Amravati
2024-2025
 Certificate
This is to certify that the seminar entitled

Recommendation systems: Building personalized experience

is a bona-fide work and it is submitted to the
Sant Gadge Baba Amravati University, Amravati
By
Mr. Sumit D. Patil
in the partial fulfillment of the degree of Bachelor of Engineering in Computer Science and
Engineering during the academic year 2024-2025 under my guidance.

Prof. V. G. Telharkar Dr. A. P. Kankale

Guide HOD/Vice-Principal
Department of CSE

Dr. A. G. Kulkarni
Principal

Department of Computer Science and Engineering

Siddhivinayak Technical Campus, Shegaon.
2024-2025
 Acknowledgement

It is pleasant endeavor to present seminar report on Recommendation systems: Building

personalized experience I avail this opportunity to express my deep sense of gratitude and
whole hearted thanks to my guide Prof. V. G. Telharkar of STC, Shegaon for substantial
guidance and cooperation in the seminar work. He has provided all the facilities whenever I need
and mostly for his gracious encouragement, advice and guidance to make this project a success.

I am equally thankful to Dr. A. P. Kankale (HOD) Dept of CSE and all the Faculties of
Computer Science and Engineering Department of STC, Shegaon for constant inspiration and
valuable suggestions.

I also express my gratitude to Dr. Anant G. Kulkarni Principal, STC, Shegaon for
constant inspiration and valuable advice.

Words fall short to express my deep sense of gratitude towards them all, who have
directly or indirectly helped in making this project.

Mr. Sumit D. Patil

Final year CSE
STC, Shegaon
TABLE OF CONTENTS

1. ABSTRACT .................................................................................................................................................1

2. INTRODUCTION ........................................................................................................................................2

3. LITERATURE SURVEY .............................................................................................................................3

4. BASIC CONCEPT OF RECOMMENDATION SYSTEM ..........................................................................5

5. APPROACHES TO RECOMMENDATION SYSTEMS ............................................................................7

5.1 Content-Based Recommendation Systems .................................................................................7

5.2. Collaborative Recommendation Systems ...................................................................................8

5.3. Hybrid Recommendations Systems ............................................................................................9

6. STEPS TO BUILD RECOMMENDATION SYSTEM..............................................................................11

Step 1: Data Collection and Preparation .......................................................................................... 11

Step 2: Selecting the Recommendation Algorithm ..........................................................................12

Step 3: Training and Evaluation of Recommendation Model .......................................................... 13

Step 4: Integration and Deployment ................................................................................................ 14

7. CHALLENGES OF RECOMMENDATION SYSTEMS ..........................................................................15

8. APPLICATION OF RECOMMENDATION SYSTEMS ..........................................................................17

9. CONCLUSION ...........................................................................................................................................20

10. REFERENCES ...........................................................................................................................................21

 LIST OF FIGURES

Figure 1: Basic Concept…………………………................................................................5

Figure 2: Classification of RS...............................................................................................7

Figure 3: Content-Based RS.................................................................................................8

.
Figure 4: Collaborative-Based RS ...................................................................................... 9

Figure 5: Hybrid RS.............................................................................................................10

 Recommendation systems: Building personalized experience

1. ABSTRACT

The Recommendation System (RS) is used to show relevant product items to the customers
according to the customer interest area. The RS is widely used in web search engines, mobile
devices. E-commerce websites, desktop applications, social media platforms, etc. The RS
significantly increases the business of e-commerce giants, prevents a user from incorrect inputs in
search engines, helps the user to find relevant content in social media platforms, assists the user
in acquiring desired outcomes in the mobile devices. We have investigated RS and their
applications from various aspects i.e. time, location, seasonal, context, social media, others, and
intended to propose the deep learning-based query auto-completion approach for the RS, which
enhances the quality and efficiency of existing RS systems.

STC/BE/CSE/2024-25 1|Page
 Recommendation systems: Building personalized experience

2. INTRODUCTION

The trend of shopping is entirely changed due to the revolution of information and
communications technology. People prefer e-commerce shopping rather than traditional physical
shopping. Recently novel virus diseases named COVID-19 1outbroke and affected the world
economy drastically. However, the usage of e-commerce is exponentially increased and became an
integral part of daily life. Global e-commerce sales reached $2.928 trillion in 2018 and raised by
20.7 % to $3.535 trillion in 2019 and economists also expected that e-commerce sales would
approach $5trillion by 2021. The volume of data and information is exponentially increasing each
second on the various kind of platforms over the internet. In this scenario, it is very important to
find relevant information from such a large amount of data.
The Recommendation Systems (RS) plays a vital role to find relevant information according to
the customers' preferences. The objective of RS is to personalized online product or service
recommendations. It has been observed that RS is the integral sale strategy of e-commerce-based
companies. Due to the wide usage and commercial importance of RS, the research community has
been working on various aspects of RS, however, it is still a challenging area of research in the
domain of information retrieval. The usage of RS is tremendously increased in e-commerce
websites, search engines, social media applications, mobile devices, mobile applications, etc. The
big tech giants do huge investments in this application of information processing areas to compete
with others. Due to the commercial importance of RS, the research community plays a vital role in
recent years. It has been observed that like other areas, deep neural networks are also widely used
in RS for the good results and high accuracy rate of prediction.

STC/BE/CSE/2024-25 2|Page
 Recommendation systems: Building personalized experience

3. LITERATURE SURVEY

Jian Wei et al. proposed the RS approach based on collaborative filtering and deep learning
techniques, and especially deal could start problem of RS systems. The proposed approach
enhances the RS systems efficiency and quality of outcomes especially in the scenario of the cold
start problems by using collaborative filtering and machine learning algorithms. They extracted
content-based features from the logs and used deep learning neural networks to formulate a
recommendation list.
Abhay E. Patil et al. proposed the RS approach based on collaborative filtering and association
rule mining. In this approach, the collaborative filtering predicts customer choices while the
association rule mining is used to know the frequent pattern in the logs. Due to the help of
collaborative filtering and association rule mining techniques, the proposed RS gives good quality
recommendations over data sparsity and cold start problems. This RS especially developed for a
recommendation of books to the online customer
Baolin Yi et al. proposed a novel RS approach named Deep Matrix Factorization (DMF) based on
deep learning and collaborative filtering. The DMF approach combines user and item information,
and implicit feedback embedding is used to transform the high dimensional information into the
vector-based dominant features. This approach predicts user interest with the help of latent factors.
S. Cao et al. proposed the deep learning and collaborative filtering-based approach for online news
RS by using the stacked auto-encoder technique. The stacked auto-encoder technique acquires the
constructive features in low dimension form from actual infrequent user-item matrices. The
experimental results showed that this approach improved the RS efficiency and quality of
recommended items.
Wang Zhou et al. proposed the RS approach based on deep learning by exploring customer
interests. This approach explores the interests of each customer and acquires aspects of text
information with the help of the convolutional neural network and apply convolutional matrix
factorization to produce the candidate list. The proposed approach increases the efficiency of the
system and generates a top-N recommendation list according to customer relevance even in the
data-sparse and cold start problem. But this approach does not deal with customer interest changes
over time.

STC/BE/CSE/2024-25 3|Page
 Recommendation systems: Building personalized experience
Nabil S et al. investigated various RS approaches and proposed combined proposed based on the
demographic filtering, collaborative filtering, content filtering, user profile, sentiment analysis of
social information for the efficient system. The objective of this approach is to prevent from cold
start problem, generate the most relevant items for the customer, minimize the search duration, and
improve the efficiency of the system.
Hwangbo et al. proposed and implemented collaborative filtering-based RS for the Korean fashion
industry. They deal with both online and offline customers and respective products. The proposed
approach named K-RecSyc uses an item-based collaborative algorithm and unifies click 9 data from
online products and sale data from offline products in the direction of knowing preferences of
customers. Experimental results showed that the proposed approach is more efficient than
traditional recommendation techniques in the case of seasonal and fashion recommendations by
using customer click data
Youdong Yun et al. stated that the collaborative filtering technique is widely used in various
applications of recommendation systems but the result is not remarkable due to insignificant
performance. As a consequence, they proposed a novel collaborative filtering-based RS by using
review data of products and evaluated the proposed model on Amazon review data.

STC/BE/CSE/2024-25 4|Page
 Recommendation systems: Building personalized experience

4. BASIC CONCEPT OF RECOMMENDATION SYSTEM

The significantly increase the usage of technology medium for various business and services
purposes, play a vital role in the development of the RS domain. The role of the user feedbacks
in the web and mobile applications acts as a catalyst in the area of RS. The recommendation has
been generated for the user and each recommendation operation has an item or the list of items.
Consequently, the RS uses the user previous session, interaction history, and contextual
information for the identification of user interest and preferences to predict user future choices.

Fig 1. Basic Concept

The online user activities carry the various kinds of intra-similarities between user and items and
the basic concept of recommendation is to identify such activities and predict the user's future
possible choices as outcomes. The user-rating metric is used to trace and identify those
intrasimilarities in a data-driven manner and then the model uses those intra-similarity features
to predict relevant items for each user. Literature studies of RS showed that if there is enough
user information then there would be more appropriate recommendations.
The usage of RS systems is tremendously increasing in recent years because of the advancement
of artificial intelligence techniques in real life. The RS based applications play a vital role to
assist the naïve user with the help of artificial intelligence algorithms. Recommendation feature-
based e-commerce websites and mobile applications predict relevant product items for the
customer with the help of customer likeness or dislike ness, comments, and responses on other
product items. Some systems also use social media information, demographic information, and
other appropriate information for the prediction of product items. The RS plays a vital role to

STC/BE/CSE/2024-25 5|Page
 Recommendation systems: Building personalized experience
find relevant information according to the customers' preferences. Recommendation feature-
based search

website prevents a user from incorrect inputs and formulates user intended queries.
Recommendation feature also helps to find a relevant prediction list over the location, time,
demography, etc. As we know mobile devices have the lowest keypad, which increases the
chances of incorrect input or mistyping, however, recommendation features in mobile devices
and mobile applications accommodate the mobile customer to step up the human-computer
interaction.
The RS problem can be defined in various ways, but two of them are described as follows:
• Prediction problem: The first problem is to predict the rating value by using the user-item
combination. It is supposed dataset shows the user has preferences for the item and a is user and
b is items then the incomplete metric would be a×b. In the scenario, the existing values are used
in the training while the missing value would be predicted by using the trained model.
• Ranking problem: The trained model has been predicted the missing values but then the
question comes how to display them to the particular user. The top-k items have been chosen
based on the user preferences for the display purpose. This problem is also known as the k-top
recommendation problem or ranking formulation problem.

STC/BE/CSE/2024-25 6|Page
 Recommendation systems: Building personalized experience

5. APPROACHES TO RECOMMENDATION SYSTEMS

The RS depends on the various type of information filtering. Information filtering deals with
information that is liked by users to find something interesting or useful for predictions and
recommendations. An information filtering judges’ user based on user-profiles by filtering and
then, as a result, give relevant information to the user. The approaches to RS are classified into
content-based, collaborative filtering, hybrid, and knowledge-based as described in Fig 2.

Fig 2. Classification of Recommendation Systems

5.1 Content-Based Recommendation Systems

It is one of the most famous techniques of RS. The content refers to the items, products, services
that are liked or responded by the customer. Then the recommendation list has been generated
according to customer existing content. Take the example of a YouTube user who likes to learn
cooking skills. This user always searches for cooking related stuff then YouTube automatically
shows a series of cooking-related videos.
The content-based RS foundation lies in the customer preferences in the past and similar to past
preferences, the new product has been recommended. The process of content-based RS is shown
in Fig 2. the user reads an article, and the system analyzes its features (such as keywords, topics,
or metadata). The system then identifies other articles with similar characteristics and
recommends them to the user, as depicted by the arrows pointing from the read article to the
suggested content. It can be seen that the interest model in the content-based RS plays a vital
role. The various kinds of similarity measures have been used to compute the similarity of two
items.

STC/BE/CSE/2024-25 7|Page
 Recommendation systems: Building personalized experience

Fig 3. Content-based RS

Content-based Filtering requires a large amount of information on items, features, aspects rather
than user interaction and feedback. It is also known as cognitive filtering. It predicts items based
on the comparison between items and user profiles. Usually, content-based filtering uses text
documents as an information source. There are various techniques for the learning of user-profiles
such as relevance feedback, neural network, Bayesian classifier, and genetic algorithm.

5.2 Collaborative Recommendation Systems

It is another famous technique of RS. It is the most successful recommendation system technique
and widely used by Facebook, Amazon, eBay, et. The collaborative based RS investigates the
items, products, services, etc with the help of feedback from other customers. Such systems filter
the other customer profiles for the prediction of the current customer. The collaborative based RS
gather the customer profile and then find the relationship between former customer profiles and
current customer profile with the help of similarity model. Collaborative filtering recommendation
are described in a diagram in Fig 4.
The collaborative RS can be divided into I. model-based and II. memory-based.
• Model-based RS:
Model-based collaborative RS describes the user-item interactions and the model is trained by the
user-item interaction metric. Both supervised and unsupervised machine learning techniques are
used in the creation of models and training and prediction phases must be separated. Model-bases
RS includes models such as regression model, support vector machine, neural networks, Bayes
classifiers, and others.

STC/BE/CSE/2024-25 8|Page
 Recommendation systems: Building personalized experience
• Memory-based RS:
Memory-based collaborative RS based on the similarities between user and item extracted during
the user-item interaction. There is no model of user-item interaction however, it based on the facts
related to similar users. There two types of memory-based RS i.e. I. user-based collaborative
filtering and II. item-based collaborative filtering where the user-based computes the ratings by
using neighborhood items while item-based computes rating by using similar user ratings.
Memory-based RS is also known as the neighborhood-based RS.
The advantage of collaborative-based RS over content-based RS is a collaborative technique also
performs well for the new customer. Consequently, the collaborative technique is widely used in
cold start problems. Collaborative Filtering (CF) based on historical data and required historical
preferences of users on the set of items. It is a technique used by various prediction systems
including RS. CF has a narrow sense and a general sense. CF based applications use large data
sets due to which CF methods are applied to various kinds of data such as e-commerce data, bank
transaction data, etc.

Fig 4. Collaborative-based RS

5.3 Hybrid Recommendations Systems

The hybrid RS based on the hybrid filtering that extracted features from two or more than two
different RS techniques such as content-based, collaborative, demographic, etc. Individual RS
generates inaccurate recommendations in the case of content and rating sparsity. The objective of
the hybrid approach is to overcome the limitation of each technique. The literature studies showed
that hybrid RS leverage the benefits of each technique to design and develop a robust system. The
generic framework of hybrid RS is shown in Fig 5.

STC/BE/CSE/2024-25 9|Page
 Recommendation systems: Building personalized experience

Fig 5. Hybrid RS
In Fig 5, it has been seen that the hybrid RS has multiple RS techniques for the generating of
recommendation. The variable “N” in the last technique of hybrid RS shows the most number of
techniques used in the particular hybrid approach and the range of N starts from the zero to the
real positive number. Mathematically it can be represented as 0≤N≤R +. The generic hybrid
approach communicates with the learning profile process in two ways and then display the
recommendations the recommendation of the online learning materials. It has been stated that
traditional RS techniques are not reliable in case of data sparsity problem. The hybrid approach
based on the content-awareness, collaborative algorithms, and the sequential pattern mining
algorithm. The content-awareness and sequential pattern mining are used to develop learning
profile and collaborative algorithms use that learning profile for the prediction of the
recommendations.

STC/BE/CSE/2024-25 10 | P a g e
 Recommendation systems: Building personalized experience

6 STEPS TO BUILD RECOMMENDATION SYSTEM

Step 1: Data Collection and Preparation

Begin by collecting relevant data, which may include user interaction data (clicks, views,
purchases), user demographic data (age, location, preferences), and item attributes (product
descriptions, categories, ratings). This data can be sourced from APIs, databases, or web scraping.

• Web Scraping
Web scraping involves programmatically accessing web pages to extract data. This is typically
done by parsing the HTML content of the page to retrieve specific data such as product details,
prices, reviews, or user- generated content. In Java, there are several libraries and frameworks
available for web scraping. Jsoup is a popular choice, known for its ability to parse HTML and
extract data. Another option is HTML Unit, which is more like a headless browser and can handle
JavaScript-rendered content. Apache HTTP Client can be used to make HTTP requests to retrieve
web pages, which can then be parsed using Jsoup or similar libraries. To build a web scraper in
Java, you’ll start by making a request to a web page using Apache HTTP Client or a similar tool.
Once you have the HTML content, you’ll use Jsoup to parse the HTML and extract the data you
need. It’s important to respect the site’s terms of service and robots.txt file when scraping. It is
also important to manage the rate of your requests to avoid overloading the server.

• Data Processing

Once the data is collected, the next critical step is data pre-processing. This involves cleaning the
data to remove inaccuracies or missing values and transforming it into a structured format, such
as CSV or JSON, that can be easily processed. Data normalization (to put all data on a common
scale) and categorization (especially for unstructured data such as text) are important aspects of
this step. Data normalization is the process of transforming data to a common scale, which helps
to compare and analyse data that was originally in different formats or scales. This is especially
important in recommendation systems where different types of data need to be compared.
Common techniques include min-max normalization, where values are scaled to a range between
0 and 1, and z-score normalization, where data points are scaled based on their mean and standard
deviation. The choice of method depends on the nature of the data and the specific requirements
of the recommendation algorithm.
There are three general best practices for data normalization:

STC/BE/CSE/2024-25 11 | P a g e
 Recommendation systems: Building personalized experience
Consistency: Apply the same normalization technique across all similar data types for
consistency.
Handling Outliers: Be mindful of outliers in your data, as they can skew the normalization
process. Sometimes, it might be necessary to handle outliers separately.
Reversibility: In some cases, you might want to reverse the normalization process to interpret the
results. Ensure that the normalization process you choose is reversible.

Step 2: Selecting the Recommendation Algorithm

Choosing the right algorithm is critical. When implementing the algorithm, the nuances of each
approach must be considered. Each offers unique advantages and works better in different
scenarios, but in most cases, the hybrid approach that combines elements of both approaches is
the best choice.

• Collaborative Filtering
When choosing a recommendation algorithm, you may want to consider collaborative filtering.
As we’ve already explained, this method makes recommendations based on the collective
preferences of other users. Item-based collaborative filtering models can be further divided into
user-based and item-based approaches. User-based focuses on finding similar users, while item-
based looks for relationships between items.

• Content Based filtering

There are also content-based methods that recommend items, such as a particular movie, by
comparing the content (attributes, descriptions) of the items themselves. If a user likes a certain
item, the recommendation system shows items with similar characteristics. It relies heavily on
extracting features from the items, which can be text-based (like keywords in a book description)
or based on other item attributes.
In Java, these algorithms can be hand-coded (by no means an optimal approach) or implemented
using libraries such as Apache Mahout (a much more desirable approach), which provides a set
of pre-built algorithms and tools for building recommendation systems.
When implementing the algorithm, the nuances of the chosen approach must be considered. If
you’re using collaborative filtering, you’ll need to create a matrix of user-item interactions. For
content-based filtering, item attributes must be converted into a machine-readable format.
Libraries like Mahout greatly simplify this process with built-in functionality.

STC/BE/CSE/2024-25 12 | P a g e
 Recommendation systems: Building personalized experience

Step 3: Training and Evaluation of Recommendation Model

The first task is to train your recommendation model on the processed data. This involves feeding
your data into the chosen algorithm and allowing it to learn from the data patterns and user
preferences. This process involves the algorithm learning from the data, identifying patterns, and
understanding relationships between different variables. The training process differs depending
on whether you’re using collaborative filtering, content-based filtering, or a hybrid approach.
After you’ve trained your model, it’s important to validate its performance. This is typically done
by dividing your data set into a training set and a test set. The model is trained on the training set
and then tested on the test set to evaluate its accuracy and effectiveness.

• Evaluation metrics include:

Precision: Precision measures the proportion of recommended items that are relevant to the user.
In the context of a recommendation engine, if the system suggests 100 items and 90 of them are
actually interesting to the user, the precision is 90%. High precision indicates that the
recommendations are generally relevant and useful.
Recall: Recall, on the other hand, assesses the proportion of relevant items that were actually
recommended by the system. For instance, if there are 100 items that should be of interest to a
user but the system only recommends 70 of them, the recall is 70%. High recall implies that the
system is effective in identifying a large number of relevant items for each user.
Mean squared error: Mean Squared Error is a common measure in predictive models, including
recommendation systems. It calculates the average of the squares of the errors or deviations (i.e.,
the difference between the predicted values and the actual values). In recommendation systems, it
can be used to measure the accuracy of predicted ratings. Lower MSE values indicate better model
accuracy.
A/B testing: A/B testing involves comparing two versions of the recommendation model to see
which performs better. In this approach, you would typically have a control group (A) and a test
group (B). Each group is exposed to a different version of the recommendation algorithm. The
performance of each version is then evaluated based on user engagement or other relevant metrics.
This method is particularly useful for practical, real-world validation of the recommendation
system.
Based on the performance in the testing phase, the model may need to be tuned. This may involve
adjusting parameters, refining the algorithm, or even revisiting the data processing step to ensure
that the data is optimally prepared for the model.

STC/BE/CSE/2024-25 13 | P a g e
 Recommendation systems: Building personalized experience

Step 4: Integration and Deployment

The final step in building a custom recommendation engine, Integration and Deployment, involves
embedding the developed system into an existing application or platform and ensuring that it
operates effectively in a real-world environment. This phase is critical because it transforms the
recommendation model from a standalone entity into a functional component of a larger system.
• API-Based Integration: -
One of the most common methods for integrating a recommendation engine with a web
application is through an Application Programming Interface (API). In this approach, the
recommendation engine is hosted as a separate service, and the web application interacts with it
via API calls. When a user interacts with the web application (like browsing products or watching
videos), the application sends a request to the recommendation engine’s API with relevant user
data. The engine processes this request, generates recommendations, and sends them back as a
response to the API call, which the web application then displays to the user.
• Embedding as a microservice: -
Another approach is to integrate the recommendation engine as a microservice within the
application’s architecture. This means the engine operates as an independent but connected part
of the larger system, often communicating with other services through internal APIs or message
queues. Microservice architecture offers scalability and flexibility, allowing the recommendation
service to be scaled independently of the rest of the application, which is beneficial for handling
varying loads and updating the recommendation logic without affecting other services.
• Direct Integration: -
For smaller applications or in cases where the recommendation engine is not expected to handle a
high volume of requests, it can be directly integrated into the web application’s codebase.
This approach involves embedding the recommendation logic and model directly within the
application’s server-side code. While this method offers simplicity and direct control, it can be
less scalable and might complicate updates to the recommendation logic.
• Deployment: -
It’s important to ensure that the deployment strategy accounts for the expected load. This involves
not just handling a large number of requests but also managing the computational load associated
with processing these requests, especially for complex algorithms. After deployment, continuous
monitoring is essential to ensure the system’s performance and availability. This includes tracking
system health, user engagement, and the accuracy of recommendations.

STC/BE/CSE/2024-25 14 | P a g e
 Recommendation systems: Building personalized experience

7 CHALLENGES OF RECOMMENDATION SYSTEMS

The RS is very effective and beneficial to find relevant information through large data. However,
the practical implementation of RS showed different kinds of challenges have occurred. The
theoretical approaches of RS seem most effective but the implementation phase suffer the various
challenges. The RS challenges include the cold start problem, ethical issues, fraud schemes, data
sparsity problem, scalability, diversity, and many others. The mentioned RS challenges are
described below.
• Cold Start Problem: -
The cold start problem is one of the major problems in the direction of RS. It has occurred when
the new users join the system without information history. In this scenario, the RS systems are not
able to generate recommendations for such new users.
It has noticed that the most effective collaborative filtering technique of RS suffers the limitation
of the cold start problem. the cold start problem solution based on the group interests in the
direction of RS. The approach focused on the hidden interests of the group where the news users
belong to formulate recommendations for them. The solution is summarized as follows:
• Identify the domain factors that can affect the new user interests.
• Create an account of a new user based on her profile attributes.
• Use new user profile attributes to find the group of existing users that is most similar to the new
user.
• Extract the group interests based on the contextual data of a new user and avoid the rating history
of new users as it is insufficient.
the item-to-item and user-to-user similarities and worked in the finding of hidden interests and
behavior of a new user based on her contextual profile.
• Ethical Issues or Privacy Concerns
The collaborative RS is entirely based on the customer data due to which major challenge of such
recommendation systems is privacy and security threats of customer information. It is essential to
take customers in confidence related usage of her personal information for prediction
recommendations and prevent a third party or malicious attacker to use customer information for
wrong means. Therefore, the research community pays attention to the privacy-preserving RS.
This was the first time in literature studies of RS when blockchain technology was used to deal
with the privacy and security concerns of users and systems. The approach uses secure multiparty
computation; privacy-preserving computation of cryptography and supported by blockchain
technology. The blockchain system (BS) is the interaction channel between customer and

STC/BE/CSE/2024-25 15 | P a g e
 Recommendation systems: Building personalized experience
company and all activities have occurred over BS. The company does not extract customer
information without permission and the customer aware of which information has been extracted
by the company.
the importance of deep learning, artificial intelligence, and blockchain technology in the e-
commerce business a secure RS method. The whole system can be categorized into the data layer,
business layer, and application layer respectively. The data layer validates user input by using
artificial intelligence and extracts various attributes with the help of deep learning. After that, the
business layer stores a user-item relation in a block of blockchain technology and generates
recommendations by using the k-mean clustering algorithm. Finally, the application layer shows
all recommendation predictions to the particular customer. This strategy prevents privacy
concerns and threats of misusing personal data by third parties or malicious attackers.
• Scalability
The RS techniques suffer the scalability problem when the existing number of users and items
significantly increased. In this situation, the execution time of each operation is exponentially
increased because the utilizing of computing resources is directly proportional to the data.
Consequently, the performance of the RS algorithms is ineffective and inaccurate. The scalability
problem depends on the performance and configuration of the computer. The literature studied
showed that the dimensional reduction method used to overcome the scalability problem in the
direction of RS. The scalability problem is also a popular challenging problem due to the massive
demand for big data applications.
• Data Sparsity Problem
The sparsity of data is a major challenge for acquiring better accuracy and performance of RS.
The RS used in commercial websites (e.g. Amazon, eBay, Netflix) has to deal with the massive
large itemset. Apart from the cold-start user, even the active user only buys one percent item from
such large itemset. If the active user wants to purchase one movie and there are 10 million movies
on the Netflix website then imaging the sparsity of the user-item matric. In the scenario, the
neighborhood algorithms are not able to compute the distance for the recommendations, and the
system becomes poor and ineffective.

STC/BE/CSE/2024-25 16 | P a g e
 Recommendation systems: Building personalized experience

8 APPLICATION OF RECOMMENDATION SYSTEMS

It is justified to say that RS-based applications have eaten the growth of traditional businesses
and services. All such practical applications of RS are part of human life and drop the significant
impact individual and collective daily routine of humans throughout the world. The research
community, big tech giants, and various governmental institutions work on the practical
applications of RS to improve them gradually. The goal of this research includes the practical
implementation of RS-based applications and improve the performance, efficiency, user
usability, etc.

Movies and Multimedia: Recommendation systems in this field play a key role in helping users
find content they would likely enjoy by analysing their past interactions. For example, platforms
like Netflix analyse your viewing history, genre preferences, and even the time spent on
particular shows or movies. The system can then suggest similar content, such as movies of the
same genre, shows featuring the same actors, or even documentaries with similar themes.
Spotify and Apple Music use similar systems for music recommendations, offering
personalized playlists such as "Discover Weekly" based on listening history, liked songs, or
similar artists. These systems help users discover new content while minimizing search time,
which is crucial for user engagement.

STC/BE/CSE/2024-25 17 | P a g e
 Recommendation systems: Building personalized experience
Tourist Locations: In the travel and tourism industry, recommendation systems are designed to
enhance the user’s travel experience by suggesting destinations, attractions, or hotels tailored to
their preferences. For instance, platforms like MakeMyTrip or Google Travel recommend tourist
spots based on a user’s past trips, reviews, or activities they’ve shown interest in. These systems
also consider user profiles, such as the type of trips you prefer (e.g., adventure, relaxation,
cultural). For example, if you previously rated several beaches highly, the system might
recommend tropical beach destinations for your next trip. This personalized approach encourages
users to explore places that match their travel interests.

OTT Platforms: Over-the-top platforms (OTT) such as Amazon Prime, and Disney+ use
advanced recommendation algorithms to personalize content for users. These systems track the
type of content a user watches, the genres they enjoy, and even what time of day they typically
watch TV. Based on this data, the platform can recommend new series or movies, ensuring that
content is always relevant to the user’s tastes. For example, if a user often watches action-packed
movies, the system will prioritize recommending action or thriller movies and shows. OTT
platforms rely heavily on such recommendations to keep users engaged and reduce churn.

Telecom: Telecom companies often face challenges in retaining customers and increasing service
usage, and recommendation systems can help address this by offering customized suggestions.
Telecom providers like MyJio and Airtel (Thanks App) use these systems to recommend mobile
plans, internet packages, or additional services based on a customer’s usage patterns. For example,
if a user consumes a large amount of mobile data for video streaming, the system might suggest
an unlimited data plan. Additionally, telecom providers might recommend value-added services,
such as international calling plans, based on the user's frequent travel habits. By offering relevant
suggestions, telecom companies aim to improve customer satisfaction and increase revenue.

E-Commerce: In online shopping, recommendation systems are a core feature that enhances the
user experience. Platforms like Amazon or Flipkart track a user’s browsing history, purchase
behavior, and even items they’ve added to their cart but didn’t buy. Based on this data, the system
suggests similar products, complementary items (e.g., recommending a laptop bag after
purchasing a laptop), or trending items in categories you’ve shown interest in. These
recommendations appear in sections such as “Customers who bought this also bought…” or
“Frequently bought together.” By suggesting products that align with user preferences, e-
commerce platforms increase the likelihood of conversions and improve customer retention.

STC/BE/CSE/2024-25 18 | P a g e
 Recommendation systems: Building personalized experience
Banking & Retail: Financial institutions and retail businesses use recommendation systems to
offer personalized financial products and shopping deals. In banking, systems analyse a user’s
spending patterns, transaction history, and financial behaviour to suggest services like credit
cards, investment products, or loans. For example, a user who spends frequently on travel might
be recommended a travel rewards credit card. In retail, systems use purchase history to suggest
relevant offers or promotions. For instance, if you often buy sportswear, the system might notify
you about an upcoming sale on fitness gear. These personalized suggestions help users discover
relevant products and services while increasing customer loyalty and engagement.

Education: Online education platforms like Coursera, Khan Academy, and Udemy have
revolutionized learning by using recommendation systems to tailor educational content to
individual learners. These platforms analyse a user’s completed courses, learning goals, and
interaction with materials to recommend new courses or learning paths. For example, after
completing an introductory course on data science, the system may recommend an advanced
course in machine learning. Furthermore, educational platforms might also suggest study
materials, tutorials, or quizzes that align with a user’s current learning progress. This
personalized learning experience helps users stay engaged and motivated while progressing in
their studies.

Food & Beverages: In the food and beverage industry, apps like Zomato, Uber Eats, and
Swiggy use recommendation systems to suggest restaurants or dishes based on a user’s location,
order history, and food preferences. For example, if you frequently order Italian cuisine, the app
might recommend new Italian restaurants in your area or even offer promotions for your
favourite meals. The system might also suggest nearby restaurants offering discounts or special
deals, tailored to the user’s dining preferences. This personalized approach not only improves
customer satisfaction but also encourages repeat orders and higher customer retention for the
platform.

STC/BE/CSE/2024-25 19 | P a g e
 Recommendation systems: Building personalized experience

9 CONCLUSION

The volume of information is exponentially increasing in each second on various kinds of platforms
over the internet. The RS makes it possible to find the relevant information from such a large amount
of data. That is the reason the RS becomes a fundamental part of the marketing strategy of each
business-centric digital organization. The online user activities carry the intraciliary features of a
customer against product items and RS used those features to predict the future possible choice of
the same customer. The approaches towards the RS are classified into content-based, collaborative
filtering, hybrid, and knowledge-based. Though the usage of the RS approaches proves the
significant increase in user satisfaction, user usability but RS domain still suffers several challenges
such as cold-start problem, privacy concerns, fraud, data sparsity, scalability, novelty, diversity,
synonymy, etc. Prediction accuracy and classification accuracy metrics are used for the evaluation
of the RS approaches. The application of RS includes web search, mobile search, music,
advertisement, trade, e-commerce, etc.

We investigated used approaches and techniques in the direction of the RS domain. The RS systems
are very effective for business-centric companies and it is an essential part of their sales strategy.
The companies not only extract customer contextual information (like age, gender, location, time,
likeness, dislike ness, search, shopping, click histories and credit card frequency), but also
community ratings, seasonal trends, domain knowledge, etc. It has been noticed that the usage of
approach depends on the type of business, business short and long-term objectives, and several
other factors.

STC/BE/CSE/2024-25 20 | P a g e
 Recommendation systems: Building personalized experience

10 REFERENCES

1.Jian Wei, Jianhua He, Kai Chen, Yi Zhou, Zuoyin Tang. Collaborative filtering and deep
learning based recommendation system for cold start items. Expert Systems with Applications
Volume 69, 1 March 2017, Pages 29-39.
2. Abhay E. Patil, Simran Patil, Karanjit Singh, Parth Saraiya, Aayusha Sheregar. ONLINE
BOOK RECOMMENDATION SYSTEM USING ASSOCIATION RULE MINING AND
COLLABORATIVE FILTERING. IJCSMC, Vol. 8, Issue. 4, April 2019, pg.83 – 87.
3. Shaowei Wang, David Lo, Bogdan Vasilescu, Alexander Serebrenik. EnTagRec++: An
Enhanced Tag Recommendation System for Software Information Sites. Article in Empirical
Software Engineering. July 2017.
4. Baolin Yi, Xiaoxuan Shen, Hai Liu, Zhaoli Zhang, Wei Zhang, Sannyuya Liu, and Naixue
Xiong. Deep Matrix Factorization With Implicit Feedback Embedding for Recommendation
System. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, VOL. 15, NO. 8,
AUGUST 2019.
5. Zhenhua Huang, Guangxu Shan, Jiujun Cheng, Jian Sun. TRec: an efficient recommendation
system for hunting passengers with deep neural networks. The Natural Computing
Applications Forum 2018.
6. SRS Reddy, Sravani Nalluri, Subramanyam Kunisetti, S. Ashok and B. Venkatesh.
ContentBased Movie Recommendation System Using Genre Correlation. Smart Intelligent
Computing and Applications. Smart Innovation, Systems and Technologies, vol 105. Springer,
Singapore.

STC/BE/CSE/2024-25 21 | P a g e