COLLEGE OF ENGINEERING AND TECHNOLOGY

Mulavoor P.O, Muvattupuzha, Kerala – 686673

COLLEGE ADVISOR FOR HIGHER STUDIES

MINI PROJECT REPORT

ANN SUSAN PETER (ICE22CS032)

AYSHA (ICE22CS048)
NADHA ALI C K(ICE22CS098)
ZENHA FATHIMA (ICE22CS120)

in partial fulfilment for the award of the degree of

BACHELOR OF TECHNOLOGY

IN

COMPUTER SCIENCE AND ENGINEERING

APJ ABDUL KALAM TECHNOLOGICAL UNIVERSITY
APRIL 2025
 COLLEGE OF ENGINEERING AND TECHNOLOGY
Mulavoor P.O, Muvattupuzha, Kerala – 686673

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

BONAFIDE CERTIFICATE

This is to certify that the project report entitled “COLLEGE ADVISOR

FOR HIGHER STUDIES” is a bonafide record of the project report
presented by ANN SUSAN PETER(ICE22CS032), AYSHA(ICE22CS048),
NADHA ALI CK (ICE22CS098), ZENHA FATHIMA(ICE22CS120), during
the academic year 2024 – 2025 towards the partial fulfilment of the
requirement of the award of B.Tech Degree in Computer Science and
Engineering of APJ Abdul Kalam Technological University,
Thiruvananthapuram.

Mrs. SHAMEENA E M Mrs. CHITHRA RANI P.R Dr. LINO ABRAHAM

VARGHESE
Assistant Professor Assistant Professor Professor & HOD
CSE Department CSE Department CSE Department

Project Guide Project Coordinator Head of the Department

 DECLARATION

We Ann Susan Peter, Aysha, Nadha Ali C K, Zenha Fathima hereby declare that, this
project report entitled “College Advisor For Higher Studies” is the bonafide work of mine
carried out under the supervision of Ms. Chithra Rani P.R. We declare that to the best of
our knowledge, the work report here in does not form part of any project report or
dissertation the basis of which a degree or award was conferred on an earlier occasion on
any other candidate the content of this report is not being presented by any other student to
this or any other university for the award of degree.

Signature:
Name of the Student: ANN SUSAN PETER
Uni.Register No: ICE22CS032
Signature:
Name of the Student: AYSHA
Uni.Register No: ICE22CS098

Signature:
Name of the Student: NADHA ALI C K
Uni.Register No: ICE21CS098

Signature:
Name of the Student: ZENHA FATHIMA
Uni.Register No: ICE22CS120

Signature:
Name of the Guide: Mrs: SHAMEENA E M

Signature:
Name of the Coordinator: Mrs: CHITHRA RANI P.R

Countersigned with Name: Dr. LINO ABRAHAM VARGHESE

HOD, Computer Science & Engineering
Ilahia College of Engineering and Technology
Date :
 Place : Muvattupuzha

ACKNOWLEDGEMENT

Apart from the efforts of our, the success of this project report depends largely on the
encouragement and guidelines of many others. We take this opportunity to express our
gratitude to the people who have been instrumental in the successful completion of
this project.

We would like to show our heartfelt gratitude towards Prof. Dr. K.A NAVAS,
Principal, Ilahia College of Engineering and Technology for granting us the
permission to work this project. Also, we would like to show our greatest gratitude
towards our head of the department of Computer Science & Engineering, Dr. LINO
ABRAHAM VARGHESE and project guide Mrs. SHAMEENA E M, Our project
Coordinators Mrs. CHITHRA RANI P.R, for their valuable advice and guidance.

Finally, we express our gratitude and thanks to all our teachers and other faculty
members of the Department of Computer Science & Engineering, for their sincere
and friendly cooperation in completing this project.

Date : ANN SUSAN PETER

Place : Muvattupuzha AYSHA

NADHA ALI C K
 ZENHA FATHIMA

ABSTRACT

Choosing the right college and course can be challenging for students, especially when
they are unsure about their career path. This project aims to simplify the decision-making
process by providing a personalized college and course recommendation system. The
system evaluates user preferences, such as location, interests, and desired college
environment, and matches them with suitable institutions and programs. Additionally, it
integrates an aptitude test that assesses students’ skills and career inclinations, helping
those who are uncertain about their academic direction.

One of the key features of this system is its ability to match colleges not only based on user
preferences but also on the results of the aptitude test, ensuring more accurate
recommendations. The aptitude test is designed to analyze a student’s skills and interests to
generate insightful results, guiding them toward the most suitable courses. The system also
offers a comprehensive database of colleges and courses, providing students with detailed
information about various programs to aid their decision-making.

The user-friendly interface ensures a seamless experience, allowing students to easily fill
out their details, take the aptitude test, and explore their results. Simplicity in design makes
navigation intuitive, making it accessible for users with varying levels of technical
expertise. Moreover, the system incorporates user feedback to improve and update
recommendations over time, ensuring continuous enhancement based on real-world usage.
By combining AI-driven insights, aptitude assessment, and user-centric recommendations,
this project offers a smart and efficient solution for students seeking guidance in higher
education choice.
 5.2 USE CASE DIAGRAM 15

5.3 SEQUENCE DIAGRAM 16

5.4 ACTIVITY DIAGRAM 18

6 IMPLEMENTATION 20

6.1 SYSTEM ARCHITECTURE 20

6.2 USER INPUT AND PREFERENCES 20

6.3 APTITUDE TEST AND AI INTEGRATION 20

6.4 RECOMMENDATION ENGINE 21

6.5 CONTINUOS LEARNING AND FEEDBACK

6.6 SECURITY AND USER AUTHENTICATION 21

6.7 DEPLOYMENT

7 DESIGN GOALS 22

8 RESULTS AND DISCUSSION 25

10 CONCLUSION AND FUTURE SCOPE 31

11 REFERENCE 33
 5.2 USE CASE DIAGRAM 15

5.3 SEQUENCE DIAGRAM 16

5.4 ACTIVITY DIAGRAM 18

6 IMPLEMENTATION 20

6.1 SYSTEM ARCHITECTURE 20

6.2 USER INPUT AND PREFERENCES 20

6.3 APTITUDE TEST AND AI INTEGRATION 20

6.4 RECOMMENDATION ENGINE 21

6.5 CONTINUOS LEARNING AND FEEDBACK

6.6 SECURITY AND USER AUTHENTICATION 21

6.7 DEPLOYMENT

7 DESIGN GOALS 22

8 RESULTS AND DISCUSSION 25

10 CONCLUSION AND FUTURE SCOPE 31

11 REFERENCE 33

12 APPENDIX 34
 LIST OF ABBREVIATIONS

ABBREVIATIONS DESCRIPTION
AI ARTIFICIAL INTELLIGENCE
API APPLICATION PROGRAMME INTERFACE
CSV COMMA-SEPARATED VALUES
GUI GRAPHICAL USER INTERFACE
HTTP HYPERTEXT TRANSFER PROTOCOL
HTTPS HYPERTEXT TRANSFER PROTOCOL SECURE
IDE INTEGRATED DEVELOPMENT ENVIRONMENT
IP INTERNET PROTOCOL
JSON JAVASCRIPT OBJECT NOTATION
ML MACHINE LEARNING
OTP ONE-TIME PASSWORD
RAM RANDOM ACCESS MEMORY
SQL STRUCTURED QUERY LANGUAGE
UI USER INTERFACE
URL UNIFORM RESOURCE LOCATOR
UX USER EXPERIENCE
 LIST OF FIGURES

Figure No. Figure Name Page No.

5.1 CIRCUIT DIAGRAM 14

5.2 USE CASE DIAGRAM 15

5.3 SEQUENCE DIAGRAM 17

5.4 ACTIVITY DIAGRAM 19
8.1 OUTPUT 1 28
8.2 OUTPUT 2 29
 COLLEGE ADVISOR FOR HIGHER STUDIES

CHAPTER 1
INTRODUCTION

This project introduces an AI-driven College and Course Recommendation System that
helps students find the most suitable academic options based on their preferences and
aptitude. The system takes into account factors such as location preference, field of interest,
and desired college environment. Additionally, an integrated aptitude test assesses students’
skills and career inclinations, ensuring that recommendations are tailored to their strengths
and goals.
Choosing the right college and course is one of the most critical decisions in a
student’s academic journey. With the increasing number of educational institutions
and diverse course options available, students often face difficulties in making an
informed choice that aligns with their interests, career aspirations, and skill sets. The
traditional approach to selecting a college involves extensive research, counseling
sessions, and reliance on word-of-mouth recommendations, which can be time-
consuming and sometimes ineffective.
The system’s key features include matching colleges based on both user preferences and test
results, analyzing students’ skills and interests to generate relevant recommendations, and
offering a vast database of college courses with detailed information. Designed with a user-
friendly interface, the platform ensures smooth navigation for students, making it easy to
enter details, take tests, and view results. Moreover, the system incorporates user feedback,
continuously refining its recommendations for better accuracy. By leveraging AI and data-
driven insights, this project aims to bridge the gap between students and their ideal academic
paths. It simplifies the decision-making process by providing personalized, reliable, and
efficient recommendations, making higher education planning more accessible and
structured.

DEPT .OF CSE, ICET 1

 COLLEGE ADVISOR FOR HIGHER STUDIES

CHAPTER 2
LITERATURE SURVEY

Our project enhances flexibility by offering multiple career pathways. Students can explore
and compare different academic routes, job prospects, and learning opportunities before
making their final choices. By providing alternative career options, our system ensures that
students can make well-informed A literature survey provides insights into existing research
and technologies related to a project. It helps identify limitations in current systems and
demonstrates how the proposed project improves upon them. Several studies have been
conducted on course and college recommendation systems, each with unique methodologies
and drawbacks. This chapter reviews five research papers, highlighting their disadvantages
and how our project addresses them.

Mohammed E. Ibrahim, in his paper “Ontology-Based Personalized Course

Recommendation Framework,” presents a course recommendation system that relies on
ontology mapping. The framework establishes structured relationships between courses
based on predefined knowledge. While this approach helps create organized
recommendations, it lacks adaptability to evolving student interests and career trends.
Additionally, real-time feedback from students is not incorporated, making the
recommendations static and less personalized.

Our project addresses this limitation by integrating continuous learning through user
feedback and an adaptive aptitude assessment. Unlike ontology-based systems, our
recommendation engine refines suggestions dynamically based on student interactions and
changing preferences. This ensures that recommendations remain relevant and personalized
over time.

DEPT .OF CSE, ICET 2

 COLLEGE ADVISOR FOR HIGHER STUDIES

Ling Huang, in “Course Prediction Approach for Optional Course Recommendation via
Cross-User Domain Collaborative Filtering,” focuses on predicting optional courses for
students based on academic performance. This system primarily considers how well
students perform in their courses without assessing the long-term impact of these courses on
their future careers. As a result, students may choose subjects that boost their grades rather
than those that align with job market demands and career growth.

Our project enhances this approach by integrating career-based recommendations. Instead

of solely considering academic success, our system suggests courses that match students’
career aspirations and industry trends. This helps students make more informed decisions
that benefit their long-term professional development.

The paper “Stacked Ranking Feature Cluster Machine Learning (SRFCML): A Novel
Method of Career Planning of College Students Based on Career Interest Assessment and
Machine Learning” by J. Electrical Systems introduces a career planning model that relies
heavily on academic performance for recommendations. While this method effectively
classifies students into career paths based on their grades, it overlooks other crucial factors
such as soft skills, leadership abilities, extracurricular activities, and hands-on project
experience. This approach may disadvantage students who excel in practical skills but
struggle with academic grading systems.

Our project takes a more holistic approach by evaluating multiple factors beyond
academics. By considering students’ soft skills, leadership experiences, extracurricular
participation, and real-world projects, our system provides well-rounded recommendations.
This ensures that students with diverse strengths receive career guidance that accurately
reflects their potential.

Rashi Goyal, in “Building a Machine Learning-Based Recommendation Engine for the

Virtual Academic Advisor System,” highlights the challenges of traditional academic
advising methods. Many institutions still rely on manual or outdated advising systems,
making it difficult for students to receive timely and personalized career guidance. Faculty
members often have a heavy advising workload, leading to inconsistent support for students.

DEPT .OF CSE, ICET 3

 COLLEGE ADVISOR FOR HIGHER STUDIES

Our project automates academic and career planning using AI-driven recommendations.
By replacing manual advising with an intelligent system, we ensure that every student
receives accurate, data-driven guidance. This reduces faculty workload while providing
students with personalized support, improving the overall advising experience.

Sri Venkata Bhavani and Likitha Vijapu, in their paper “Machine Learning-Based
Recommendations to Aid Educational Planning and Academic Advising Through the
Virtual Academic Advisor System,” propose a Virtual Academic Advisor (VAA) system.
While this system offers structured recommendations, it follows a single predefined path for
students, limiting their ability to explore alternative career options or academic routes. This
restricts students from comparing different academic plans and job prospects before making
decisions., adaptable decisions based on their personal interests and market trends.

DEPT .OF CSE, ICET 4

 COLLEGE ADVISOR FOR HIGHER STUDIES

CHAPTER 3
PROPOSED SYSTEM

3.1 INTRODUCTION
The proposed system is a web-based College Advisor System designed to assist students in
selecting suitable colleges and courses based on their preferences, interests, and aptitude test
results. The platform leverages a recommendation engine to provide personalized
suggestions, helping students make informed decisions about their academic future.

Objectives
• To provide personalized college recommendations based on student preferences such
as location, affordability, ranking, and ambience.
• To integrate an aptitude test module to guide students unsure of their career path.
• To maintain a comprehensive database of colleges, programs, and admission details.
• To offer a user-friendly interface for easy navigation and interaction.
• To allow administrative control over database updates and user authentication.

Features of the Proposed System

1. Aptitude Test Module:
• Assesses a student’s skills, interests, and career inclinations.
• Analyzes responses to generate career and course recommendations.
2. College Recommendation System:
• Matches students with suitable colleges based on preferences and aptitude results.
• Allows students to filter colleges by affordability, ranking, and location.
3. Admin Panel for Management:
• Provides functionalities to update college details.
• Manages user authentication, including OTP verification via Twilio.
4. User Authentication & Security:
• OTP-based login system for enhanced security.
• Secure user data storage with Firebase security rules.

DEPT .OF CSE, ICET 5

 COLLEGE ADVISOR FOR HIGHER STUDIES

3.2 ADVANTAGES
 Personalized Recommendations:
The system provides tailored college and course suggestions based on user preferences
and aptitude test results, ensuring students receive recommendations that align with their
interests and skills.
 Career-Oriented Approach:
Unlike traditional systems that focus only on academic performance, this system
considers career aspirations and industry trends, helping students make informed
decisions for long-term success.
 AI-Driven Insights:
The system uses artificial intelligence to analyze data and refine recommendations
over time, making suggestions more accurate and adaptive.
 Comprehensive Course and College Database:
The platform provides detailed information on colleges, courses, eligibility criteria,
fees, and job prospects, making it a one-stop solution for students.
 User-Friendly Interface:
The system is designed with simple navigation, allowing students to easily fill in
details, take aptitude tests, and explore recommendations without technical difficulties.
 Feedback Integration:
The system continuously improves by incorporating user feedback, ensuring
recommendations remain relevant and up to date.
 Flexible Career Pathways:
Students can explore multiple career options, compare academic plans, and make well-
informed choices rather than being restricted to a single recommendation.
● Reduces Dependence on Manual Advising:
Automating the recommendation process reduces the workload on faculty and career
advisors, ensuring every student receives equal guidance.

DEPT .OF CSE, ICET 6

 COLLEGE ADVISOR FOR HIGHER STUDIES

3.3 DISADVANTAGES
● Dependence on user input:
The accuracy of recommendations depends on the information provided by users.
Incorrect or incomplete inputs may lead to less relevant suggestions..

● Limited to available data:

The system relies on its database for college and course recommendations. If
certain colleges or courses are missing, students may not receive a fully comprehensive
list of options.
● Internet Dependency:
Since the system is web-based, students need a stable internet connection to
access recommendations, which may be a limitation in areas with poor connectivity.

CHAPTER 4

DEPT .OF CSE, ICET 7

 COLLEGE ADVISOR FOR HIGHER STUDIES

SYSTEM REQUIREMENTS
The College Advisor System requires a well-defined set of hardware and software
components to ensure smooth operation. The requirements are classified into functional and
non-functional requirements, along with hardware and software specifications.

4.1 HARDWARE REQUIREMENTS

The Hardware required for the project are:

● Processor:

Minimum Requirement: An Intel Core i3 processor or an equivalent is required to run

the system at a basic level.

Recommended Requirement: For improved processing speed and performance, an

Intel Core i5 processor or higher is preferred. This ensures that the recommendation
algorithm and database queries run efficiently without delays.
● RAM (Random Access Memory):
Minimum Requirement: 4 GB of RAM is necessary to handle basic system
operations, including user authentication, data retrieval, and college
recommendations.

Recommended Requirement: 8 GB or higher is recommended to ensure smoother

multitasking, faster data processing, and better responsiveness when handling large
volumes of users.
● Storage:
Minimum Requirement: The system requires at least 20 GB of storage space,
primarily for storing user details, college information, and aptitude test results.

Recommended Requirement: To enhance performance and ensure faster data access,

a 50 GB SSD (Solid-State Drive) is recommended. SSDs significantly improve
system speed and reduce data retrieval times compared to traditional HDDs.
● Internet Connection:

DEPT .OF CSE, ICET 8

 COLLEGE ADVISOR FOR HIGHER STUDIES

Minimum Requirement: A basic internet connection is required for OTP-based

authentication, fetching data from the database, and updating user recommendations.

Recommended Requirement: A high-speed broadband connection is highly

recommended to ensure real-time updates, seamless data processing, and
uninterrupted access to cloud-based features.

 Display Resolution:
Minimum Requirement: The system should support a minimum display resolution of
1366 × 768 pixels to ensure clear visibility of the user interface and system elements.

Recommended Requirement: A 1920 × 1080 resolution or higher is preferred to

enhance user experience, making navigation smoother and ensuring that all UI
elements are displayed properly without distortion. A tiny component with a big role
in the world of electronics.

4.2 SOFTWARE REQUIREMENTS

The software requirements of the project are:

● Frontend Technologies:
The system’s frontend should be designed using modern web technologies to ensure
an interactive and responsive user interface.
• Languages: HTML, CSS, JavaScript
• Frameworks: React.js (recommended for better UI performance and user
experience)
• Browser Compatibility: The system should work seamlessly on the latest
versions of Google Chrome, Mozilla Firefox, and Microsoft Edge.

 Backend Technologies:
The backend must be capable of handling multiple user requests simultaneously while
ensuring fast and secure data processing.
• Programming Language: Node.js

DEPT .OF CSE, ICET 9

 COLLEGE ADVISOR FOR HIGHER STUDIES

• Framework: Express.js (for handling API requests efficiently)

• Authentication: Twilio API (for OTP-based login authentication)
Database & Data Storage :
The system needs a secure and scalable database for storing user data, aptitude test
results, and college details.
• Database: Firebase (for real-time data storage and retrieval)
• Security: Implementing Firebase security rules and data encryption to ensure
data privacy
• Backup: Cloud-based backup solutions to prevent data loss
Hosting & Deployment:
To ensure accessibility and ease of deployment, a reliable hosting platform must be
chosen.
• Hosting Service: Firebase Hosting (for seamless integration with the database)
• Version Control: GitHub (for managing source code an

4.3 EXPECTED SYSTEM REQUIREMENTS

The College Advisor System requires a well-defined set of hardware and software
components to ensure smooth operation. The requirements are classified into functional and
non-functional requirements, along with hardware and software specifications.

1. Functional Requirements

These define the essential functionalities of the system that enable it to operate effectively.

DEPT .OF CSE, ICET 10

 COLLEGE ADVISOR FOR HIGHER STUDIES

● REQ 1: User Authentication & Access

Users must be able to register and log in securely using OTP verification Admins
should have role-based access to manage college data.

● REQ 2: Aptitude Test & Career Analysis

The system should present a structured questionnaire to evaluate student
interests.Based on responses, the system should analyze and suggest career paths.Test
results must be stored in the database for future reference.

● REQ 3: College Recommendation System

Users should be able to input their preferences (location, budget, course, etc.). The
system should fetch relevant college details based on the user’s inputs and test
results.College listings should include rankings, affordability, and amenities.

● REQ 4: Admin Management:

Admins should be able to add, update, and delete college details.The system should
allow modification of course offerings and rankings

● REQ 5: Secure Database Management:

The system should store user details, aptitude test results, and college data
securely.Data should be retrieved and displayed efficiently to ensure a smooth
experience.

DEPT .OF CSE, ICET 11

 COLLEGE ADVISOR FOR HIGHER STUDIES

CHAPTER 5
SOLUTION METHODOLOGY

5.1 ARCHITECTURE DESIGN

Architecture design, often referred to simply as "design" in the context of architecture and
engineering, is the process of conceiving, planning, and detailing the structural and
functional elements of a system, building, or product. It involves creating a blueprint or
roadmap that outlines how various components will be organized and interact to achieve
specific objectives or requirements. The figure 5.1 shows the architecture design of the
system

DEPT .OF CSE, ICET 12

 COLLEGE ADVISOR FOR HIGHER STUDIES

DEPT .OF CSE, ICET 13

 COLLEGE ADVISOR FOR HIGHER STUDIES

Figure 5.1: Architecture Design

DEPT .OF CSE, ICET 14

 COLLEGE ADVISOR FOR HIGHER STUDIES

5.2 USE CASE DIAGRAM

A user case diagram for a college advisor illustrates the various use cases or functionalities
of the system and how different actors interact with it. The figure 5.2 shows the use case
diagram of the system.

Figure 5.2: Use Case Diagram

DEPT .OF CSE, ICET 15

 COLLEGE ADVISOR FOR HIGHER STUDIES

5.3 SEQUENCE DIAGRAM

A sequence diagram for college advisor for higher studies provides a dynamic view of how
various components of the system interact. The figure 5.3 shows the sequence diagram of
the system.

DEPT .OF CSE, ICET 16

 COLLEGE ADVISOR FOR HIGHER STUDIES

Figure 5.3: Sequence Diagram

DEPT .OF CSE, ICET 17

 COLLEGE ADVISOR FOR HIGHER STUDIES

5.4 ACTIVITY DIAGRAM

An activity diagram for a college advisor for higher studies provides a visual representation
of the different activities or steps involved It depicts the flow of control and data between
these activities, showing decision points, parallel activities, and the order in which activities
are executed. In such a diagram, each activity is represented by a rounded rectangle, and
arrows depict the flow of control or transitions between activities. Decision points are
represented by diamonds, and control flows along different branches based on conditional
logic. Fork and join symbols indicate parallel activities that can occur concurrently and
synchronize at join points. The figure 5.4 shows the activity diagram of the system.

DEPT .OF CSE, ICET 18

 COLLEGE ADVISOR FOR HIGHER STUDIES

Figure 5.4: Activity Diagram

DEPT .OF CSE, ICET 19

 COLLEGE ADVISOR FOR HIGHER STUDIES

CHAPTER 6
IMPLEMENTATION
This chapter outlines the key components and functionalities implemented in the College and
Course Recommendation System, which provides personalized academic recommendations
based on student preferences and aptitude assessments.

6.1 SYSTEM ARCHITECTURE

● Frontend: The user interface is developed using HTML, CSS, and JavaScript to ensure
that students can easily interact with the system by entering personal preferences,
completing the aptitude test, and viewing the results.
● Backend: Developed using Node.js, the backend processes user inputs, integrates the
Twilio API for OTP verification, and interacts with the database.
● Database: MongoDB is used to store user data, including preferences, test results, and
a database of colleges and courses.

6.2 USER INPUT AND PREFERENCES

● Students input their preferences such as location, field of interest, and desired college
environment through easy-to-use forms on the frontend. This data is sent to the
backend where it is processed for generating personalized recommendations.

6.3 APTITUDE TEST AND AI INTEGRATION

● An aptitude test is integrated into the system to assess students’ skills and career
inclinations. The system uses basic AI/ML models to analyze test results and match
students with colleges and courses that align with their strengths and career goals.

6.4 RECOMMENDATIONS ENGINE

● The heart of the system lies in the recommendation engine, which combines
user preferences and aptitude test results to provide college and course suggestions.
The engine’s logic ensures that suggestions are relevant by considering academic
performance, career aspirations, and location preferences.

DEPT .OF CSE, ICET 20

 COLLEGE ADVISOR FOR HIGHER STUDIES

6.5 CONTINOUS LEARNING AND FEEDBACK

● The system continuously refines recommendations based on user feedback. As
students interact with the platform and provide input on the relevance of
suggestions, the AI engine updates and improves future recommendations, ensuring
greater accuracy over time.

6.6 SECURITY AND USER AUTHENTICATION

● The system uses Twilio for OTP-based user authentication to ensure that each
student’s account is secure and that only verified users can access the system.

6.7 DEPLOYMENT

● The entire system is deployed on a cloud platform such as Heroku or AWS,

ensuring that it is scalable and accessible to students from different geographical
regions

CHAPTER 7

DEPT .OF CSE, ICET 21

 COLLEGE ADVISOR FOR HIGHER STUDIES

DESIGN GOALS

The design goals for the College and Course Recommendation System focus on
creating a seamless, intuitive, and adaptive platform that helps students make informed
academic decisions based on their preferences and aptitude. The system integrates AI,
real-time feedback, and user-centric features to provide personalized, accurate, and
reliable recommendations. Below are the key design goals:

● User Input and Interactions:

• Ease of Use: The platform should be intuitive and user-friendly, ensuring that
students of all technical backgrounds can easily navigate through the system, input
preferences, and complete the aptitude test.

• Flexibility: Allow students to customize their preferences, including location, field

of interest, and desired college environment, for more tailored recommendations.

• Engagement: Establish an interactive and engaging experience that encourages

students to complete the aptitude test and provide feedback for continuous
improvement of the system.

● Recommendation Engine:
• Accuracy: The recommendation engine should analyze both user
preferences and aptitude test results to provide highly relevant college and

course suggestions.

• AI Driven Adaptability: Implement an AI model that dynamically

refines recommendations based on user feedback and industry trends,
ensuring that the suggestions remain up-to-date and personalized

DEPT .OF CSE, ICET 22

 COLLEGE ADVISOR FOR HIGHER STUDIES

• Holistic Assessment: Provide well-rounded recommendations by

considering various factors such as skills, career goals, and academic interests
to ensure that the system accommodates diverse student.

● Security and User Authentication:

• Data Privacy: Ensure that all user data, including personal preferences
and test results, is securely stored and handled in compliance with privacy
regulations.

• Authentication: Use Twilio for secure OTP-based verification to confirm

user identities and maintain system integrity.

● Database Management:
• Scalability: Use MongoDB to manage large volumes of user data,
including preferences, test results, and college/course information, with easy

scalability for future expansion

• Efficiency: Optimize database queries for fast data retrieval, ensuring that
the system can handle concurrent user interactions smoothly.

● System Performance and Scalability:

• Response Time: Ensure that the system provides quick responses to user
inputs and recommendation queries, providing a smooth user experience.

• Scalability: Design the system to be scalable to handle an increasing

number of users and colleges/courses as the platform grows.

• Customization: Provide options for customizing the output format based

on user preferences.

● Feedback and Continuous Improvement:

DEPT .OF CSE, ICET 23

 COLLEGE ADVISOR FOR HIGHER STUDIES

• Real Time Feedback: Incorporate a mechanism for collecting user

feedback on recommendations, ensuring that the system learns and improves
over time.

• Personalization: The system should continuously adapt based on

feedback to fine-tune recommendations and provide more accurate results
with each user interaction.

● Output and Visualization:

• Clear Results: Display college and course recommendations in an easy-
to-understand format with detailed information, including eligibility, fees,
and job prospects.

• Comparative Insights: Allow users to compare different college and

course options based on key factors, helping them make well-informed

decisions.

CHAPTER 8

DEPT .OF CSE, ICET 24

 COLLEGE ADVISOR FOR HIGHER STUDIES

RESULTS AND DISCUSSION

The Results and Discussion chapter analyzes the effectiveness and performance of the
College and Course Recommendation System. This section evaluates the system’s
functionality, user feedback, and future improvements.

• Data Analysis:

• The system processes user inputs, including preferences for location, field of interest,
and desired college environment, along with aptitude test results.

• Data analysis involves evaluating how well the system can match users to appropriate
colleges and courses. Various metrics, such as accuracy of recommendations, speed of
processing, and relevance of results, are considered.

• Statistical tools and data visualization techniques like graphs and charts are used to
identify trends and patterns in the data, helping to measure how well the system meets
student needs.

• Evaluation of Recomendations:

• The college and course recommendations generated by the system are analyzed for
their accuracy, diversity, and relevance to students’ profiles.

• The effectiveness of the recommendation engine is evaluated by testing it with a

diverse set of user inputs, ensuring that it provides suitable options for a variety of
preferences and career goals.

• The Performance is assessed based on user satisfaction with the results, the relevance
of suggestions, and whether the recommendations align with the user’s expectations
and aptitude.

DEPT .OF CSE, ICET 25

 COLLEGE ADVISOR FOR HIGHER STUDIES

• Performance Metrics:

• Accuracy of Recommendations: The system’s ability to suggest relevant colleges and

courses based on user preferences and aptitude test results is quantitatively measured..

• The time taken to process user inputs and generate recommendations is measured. A
quick response time is essential for maintaining a seamless user experience.

• Surveys and feedback are collected from users to gauge their satisfaction with the

recommendations and overall system performance.

• Any inconsistencies in the recommendations or issues with processing are

documented and evaluated.

• Future Improvements:

• The Advanced AI/ML Models: Integrating more sophisticated machine learning

algorithms can improve the accuracy of the aptitude test and better match users to
colleges and courses.

• Personalization: Allowing deeper personalization options, such as feedback loops and

the ability to save preferences for future use, would enhance the user experience.

• User Feedback Mechanism: Implementing a system for continuous feedback and

allowing users to adjust recommendations in real-time would refine the system’s
adaptability.

• Discussion of Limitations:

DEPT .OF CSE, ICET 26

 COLLEGE ADVISOR FOR HIGHER STUDIES

• The accuracy of the aptitude test can be influenced by the simplicity of the AI model
used, which may not fully capture complex career preferences.

• The system might face challenges in accurately predicting user preferences when the
input data is incomplete or ambiguous.

• User Feedback and Experience:

• User Feedback: Students provided feedback about the system’s usability, the accuracy
of the recommendations, and the ease of navigation. Positive feedback was received
regarding the intuitive interface and helpfulness of the aptitude test

• User Experience: Users expressed satisfaction with the personalized nature of the
recommendations, but some suggested adding more filters for course selection, such as
career growth potential and geographical preferences.

• Impact: The system effectively helped students make informed decisions, and it was
particularly beneficial for students uncertain about their career path or college
selection.

• Output: The figure 8.1 & figure 8.2 shows the output obtained.

DEPT .OF CSE, ICET 27

 COLLEGE ADVISOR FOR HIGHER STUDIES

Figure 8.1: Output 1

DEPT .OF CSE, ICET 28

 COLLEGE ADVISOR FOR HIGHER STUDIES

Figure 8.1: Output 1

• Conclusion and Recommendations:

DEPT .OF CSE, ICET 29

 COLLEGE ADVISOR FOR HIGHER STUDIES

• Conclusion: The College and Course Recommendation System successfully helps

students make informed academic decisions. The integration of AI for personalized
recommendations based on user preferences and aptitude test results provides a
practical tool for students in their academic planning.

• Recommendations for Improvement: Future development should focus on refining the

AI models, expanding the database of colleges and courses, and enhancing the user
feedback system to continuously improve recommendations.

The Results and Discussion chapter highlights the effectiveness of the system, its
strengths, and areas for improvement. By evaluating user feedback, performance metrics,
and potential limitations, the chapter guides further development of the system to meet the
evolving needs of students.

CHAPTER 10

DEPT .OF CSE, ICET 30

 COLLEGE ADVISOR FOR HIGHER STUDIES

CONCLUSION AND FUTURE SCOPE

The College and Course Recommendation System has strong potential for growth and
improvement, offering many opportunities for future enhancements. Below are some key
areas that can be explored to further enhance the platform:

● Enhanced Recommendation System: While the current recommendation

system leverages user preferences and aptitude test results, future enhancements can
incorporate more sophisticated machine learning algorithms. By using more
advanced AI models, such as deep learning, the system can provide even more
personalized and accurate recommendations that adapt to students’ evolving
preferences over time.

● Multi-language Support: To reach a global audience, the system could

integrate multi-language support, allowing users from different linguistic
backgrounds to interact with the platform. This would make the system more
inclusive, helping non-English speaking students access and benefit from the tool.
● Real-time Admission Update: Integrating real-time admission data will allow
students to get updated information about application deadlines, seat availability, and
other crucial details. This could further enhance the system’s usefulness by helping
students plan their applications and decisions more effectively.

● Advanced Security Measures: As the system deals with sensitive user data, it
is critical to enhance security features. Implementing features such as two-factor
authentication, encryption of sensitive data, and regular security audits will help

protect user privacy and make the platform more trustworthy

● Integration with Smart Devices: Developing a mobile version of the

recommendation system will make it more accessible to students on the go. This will
ensure users can quickly access their recommendations, track updates, and receive
real-time notifications, making the system even more convenient for students with
busy schedules

DEPT .OF CSE, ICET 31

 COLLEGE ADVISOR FOR HIGHER STUDIES

● User Engagement Features: Incorporating Student Reviews: Allow students

to share their experiences with specific colleges and courses, helping future users
make better-informed decisions.

● Expanded College Database: To improve the breadth of recommendations, the

system can integrate a larger database of colleges and courses. This expansion should
include institutions across more countries, as well as specialized programs,
certifications, and vocational courses. By doing so, students will have a broader
range of choices, including options they may not have considered otherwise.

Overall, by incorporating these improvements, the College and Course Recommendation

System can become an even more powerful tool, offering students a comprehensive,
dynamic, and secure platform for navigating their educational journeys

REFERENCE

DEPT .OF CSE, ICET 32

 COLLEGE ADVISOR FOR HIGHER STUDIES

[1] Mohammed E Ibrahim, Yanyan Yang, David L Ndzi, Guangguang Yang,

Murtadha Al-Maliki
"Ontology-based personalized course recommendation framework" IEEE Access 7,
5180-5199, 2018
https://ieeexplore.ieee.org/abstract/document/8587168/
[2] Lian Huang, Chang-Dong wang, Hong-Yang Chao, Jian-Huang Lai, Philip S Yu "A
score prediction approach for optional course recommendation via cross-user-domain
collaborative filtering, IEEE Access 7, 19550-19563, 2019
https://iecexplore.ieee.org/abstract/document/8636939/
[3] Journal of electrical systems 20 (3), 1659-1669, 2024 "stacked ranking feature clustwr
machine learning(Srfcml):A novel method of career planning of college students
based on career interest assessment and machine learning
[4] Rashi Goyal "building a machine learning based recommendation engine for the virtual
academic advisor system"
https://digital.lib.washington.edu/researchworks/bitstream/handle/1773/42262/
Goyal_washington_02500
18948.pdf?sequence=1
[5] JSVBL Vijjapu-2019"Machine Learning based recommendations to aid educational
planning and academic advising through the virtual academic advisor system.
https://digital.lib.washington.edu/researchworks/bitstream/handle/1773/44137/
Vijjapu_washington_02500
20261.pdf?sequence=1

APPENDIX 1

DEPT .OF CSE, ICET 33