DECLARATION

We, T K Rushyanth Kumar (U18IW22S0017) & Keerthana S (U18IW22S0036), of VI

Semester BCA hereby declare that the project “Career Recommendation System” is carried
out and completed successfully by us during the academic year 2024-25 under the
supervision of Mrs. Marry Stella, Assistant Professor, Department of Computer Science
and Applications, St. Francis College. This project report has not been submitted for the
award of any Degree, Diploma, Associateship, Fellowship, etc., of any other University or
Institute.

T K Rushyanth Kumar

Keerthana S

Mrs. Marry Stella

i
 ACKNOWLEDGEMENTS

We are am very thankful to our project guide Mrs. Marry Stella for her invaluable
guidance, support and encouragement. We would like to thank her for providing the
required direction and motivation.

We are thankful to the Management and Department of Computer Science and

Applications, St. Francis College for providing the required resources and the
infrastructure to carry out our work. We thank our HOD Mrs. Sabitha S, for her valuable
feedback and inputs.

We thank the staff of the Department of Computer Science and Applications for their
guidance and support.

We are eternally thankful to the Almighty for making it all feasible.

T K Rushyanth Kumar

Keerthana S

ii
TABLE OF CONTENTS

DECLARATION………………………………………………………………………….i

ACKNOWLEDGEMENTS………………………………………………………………ii

TABLE OF CONTENTS………………………………………………………………...iii

LIST OF FIGURES………………………………………………………………………iv

LIST OF TABLES……………………………………………………………………….vii

ABSTRACT…………………………………………………………………………….....1

CHAPTER 1: INTRODUCTION…………………………………………………………3

1.1 BACKGROUND AND CONTEXT:

1.2 PROBLEM STATEMENT:
1.3 OBJECTIVES AND SCOPE OF THE PROJECT:
1.4 METHODOLOGY AND APPROACH:
1.5 LITERATURE SURVEY:
CHAPTER 2: SYSTEM DESIGN AND IMPLEMENTATION………………………..13

2.1 SYSTEM ARCHITECTURE AND COMPONENTS:

2.2 SYSTEM REQUIREMENT SPECIFICATIONS:
2.3 USER INTERFACE DESIGN:
2.4 ER DIAGRAM AND DATA FLOW DIAGRAMS (DFDS):
2.5 IMPLEMENTATION DETAILS:
CHAPTER 3: CODE SNIPPET AND TESTING……………………………………….57
3.1 MODULES EXPLANATION WITH SCREENSHOTS OF PROJECT:
3.2 CODE:
3.3 TESTING RESULTS:
CHAPTER 4: CONCLUSION AND FUTURE ENHANCEMENTS…………………..89

4.1 SUMMARY OF THE PROJECT’S OBJECTIVES, METHODOLOGY

AND KEY FINDINGS:

iii
4.2 CONTRIBUTION AND SIGNIFICANCE OF THE PROJECT:
4.3 LIMITATIONS:
4.4 FUTURE ENHANCEMENTS:
REFERENCE:…………………………………………………………………………...97

iv
LIST OF FIGURES

Figure 1.1:………………………………………………………………………………37
Figure 1.2:………………………………………………………………………………38
Figure 1.3:………………………………………………………………………………39
Figure 1.4:………………………………………………………………………………40
Figure 1.5:………………………………………………………………………………41
Figure 1.6:………………………………………………………………………………42
Figure 1.7:………………………………………………………………………………43
Figure 1.8:………………………………………………………………………………44
Figure 1.9:………………………………………………………………………………45
Figure 2.0:………………………………………………………………………………46
Figure 2.1:………………………………………………………………………………47

v
LIST OF TABLES

Table 1.1:………………………………………………………………………………….8
Table 1.2:………………………………………………………………………………...10
Table 1.3:………………………………………………………………………………...17
Table 1.4:………………………………………………………………………………...19
Table 1.5:………………………………………………………………………………...20
Table 1.6:………………………………………………………………………………...35
Table 1.7:………………………………………………………………………………...48
Table 1.8:………………………………………………………………………………...52
Table 1.9:………………………………………………………………………………...88

vi
 ABSTRACT

In today’s fast-evolving job landscape, students and early-career individuals are often
confused and overwhelmed by the wide array of career paths and the lack of tailored
guidance. Traditional career counseling methods fail to meet the unique academic
backgrounds, interests, and aspirations of each user. This project addresses that gap by
developing an intelligent Career Recommendation System that offers personalized
career suggestions based on a user’s subject knowledge, completed academic courses, and
interests. The system caters to educational institutions, individual learners, and career
development platforms, with high social relevance, particularly in helping bridge the gap
between education and employability. The emergence of data-driven career planning,
adaptive learning, and has created new opportunities for innovation. The main objective of
the project is to guide users towards suitable career paths while identifying and helping
them close existing skill gaps. The motivation for this project stems from the urgent need
for integrated career tools that not only advise but also prepare users for their professional
journey through assessment and documentation support.

The methodology involves a hybrid recommendation engine implemented in Python,

which uses similarity-based logic to match user inputs to suitable job roles and identify
required skills or courses. The platform incorporates dynamic domain-specific quizzes
(stored in JSON) to assess user knowledge, and based on performance, it also recommends
internships. Additional features include a “Resume Builder” and a “Project Report
Generator”, enhancing the platform’s utility. The web application uses PHP for backend
development, Tailwind CSS for the responsive frontend, and the mPDF library to generate
formal academic PDF reports. Assumptions include basic user familiarity with web forms
and subject knowledge, and constraints include limited access to real-time job databases or
third-party course platforms. The structured workflow begins with data collection from the
user, followed by career matching, quiz-based evaluation, result analysis, and finally,
resume/report generation. This sequence ensures a seamless and interactive user experience
while maintaining academic and professional standards throughout.

1
 CHAPTER 1: INTRODUCTION
The Career Recommendation System is a smart web-based platform designed to help
students and job seekers identify the most suitable career paths based on their interests,
completed courses, and knowledge levels. It goes beyond traditional career guidance by
providing personalized job role suggestions, identifying missing skills, offering domain-
specific quizzes, and recommending internships. Additionally, the system includes tools
for resume creation and formal project report generation, making it a comprehensive career
planning assistant. Built using PHP, Python, and Tailwind CSS, this project aims to bridge
the gap between academic learning and real-world career opportunities through
intelligent automation.

1.1 BACKGROUND AND CONTEXT:

In today’s rapidly evolving job market, students and early-career professionals face
increasing difficulty in identifying the right career paths, relevant skill sets, and suitable
internship opportunities. Traditional job search platforms often lack personalization and
fail to account for an individual's learning history, interests, and geographical constraints.
This creates a gap between academic learning and real-world employment expectations,
making it challenging for learners to align their skills with industry requirements.

To address this challenge, recommendation systems—especially those powered by

artificial intelligence and data science—have emerged as effective tools for personalized
guidance. These systems analyse user behaviour and item attributes to suggest courses,
internships, and jobs that closely match an individual's profile. However, many existing
systems rely solely on either user behaviour or item features, limiting the accuracy and
relevance of their suggestions.

This project introduces a Course and Internship Recommendation System that bridges this
gap using a hybrid recommendation model, combining both Collaborative Filtering and
Content-Based Filtering techniques. Unlike conventional models, this system not only
analyses past user activity but also considers detailed attributes of learning content and job
listings. It integrates user input on interests, completed courses, preferred job roles, and
geographic preferences to generate customized recommendations.

2
1.2 PROBLEM STATEMENT:

In today’s fast-paced and competitive environment, students and early-career professionals

often lack the necessary guidance to make informed career decisions. Despite having
access to various educational resources and platforms, many struggle to align their
academic background, skills, and interests with appropriate job roles. Traditional career
counselling methods are often generalized, outdated, and unable to provide personalized
suggestions based on individual strengths and aspirations.

• Lack of personalized career guidance tailored to individual interests and academic

background.
• Inability to identify the exact skills or courses required for specific job roles.
• Absence of tools to assess current knowledge or job-readiness through structured
testing.
• Difficulty in accessing real-time, relevant internship recommendations.
• Challenges in preparing professional resumes and formal academic reports.
• No centralized system to track and analyse user activities for administrators or
educators.

These issues result in confusion and misdirection, often leading students to pursue careers
they are not suited for or prepared to enter. Traditional career counselling methods are
typically one-size-fits-all and do not cater to the unique needs of each learner.

To overcome these challenges, there is a strong need for an integrated and intelligent
system that offers personalized career recommendations, evaluates skill gaps, and supports
users in building both their professional identity and readiness. The proposed Career
Recommendation System addresses this gap by providing a unified platform that combines
career suggestions, skill assessment, internship guidance, and documentation tools—
empowering users to make well-informed decisions about their futures.

3
1.3 OBJECTIVES AND SCOPE OF THIS PROJECT:

Objectives

The primary goal of the Career Recommendation System is to guide users in selecting the
most suitable career paths based on their individual interests, completed academic courses,
and current knowledge. The system aims to bridge the gap between education and industry
expectations through a personalized, interactive, and intelligent platform.

Key objectives include:

➢ Recommend career paths tailored to user interests and academic history.

➢ Perform skill gap analysis by comparing current courses with job requirements.
➢ Provide domain-specific quizzes to evaluate user knowledge.
➢ Suggest internships based on quiz performance and career interests.
➢ Enable users to build professional resumes with downloadable options.
➢ Generate formal project reports in standard academic formats using mPDF.
➢ Equip administrators with tools to track and monitor user activity (login times,
course visits, quizzes taken, internships explored, etc.).

Scope

This project is designed as a full-featured, web-based platform built with PHP, Python,
MySQL, and Tailwind CSS. It targets students, recent graduates, and job seekers aiming
to make informed career decisions.

The scope of the system includes:

➢ A dynamic user dashboard for career role suggestions based on selected interests
and completed courses.
➢ Integration with structured databases (e.g., job roles, skills, and course
requirements).
➢ A modular quiz system that draws from JSON data based on job role selection.
➢ Internships shown only when a user scores above a set threshold.
➢ Resume builder and report generator for creating downloadable documents in
professional formats.

4
 ➢ An admin module that displays complete user activity logs for analysis and
management.

Through this wide-ranging scope, the Career Recommendation System functions not only
as a guidance tool but also as a preparatory assistant that helps users move closer to their
professional goals.

1.4 METHODOLOGY AND APPROACH:

This project was executed using a “hybrid, incremental methodology” that blends elements
of the traditional Waterfall model (to preserve clear documentation and sign-off points)
with Agile iterations (to enable rapid prototyping, user feedback, and continuous
improvement). The overall workflow is divided into five macro-phases—“Planning &
Analysis, Design, Development, Testing, and Deployment & Maintenance”—with short
two-week sprints inside the Development phase to deliver working increments of the
system.

a) Planning & Requirement Analysis

➢ Stakeholder Interviews & Surveys – Conducted structured interviews with students,

placement officers, and recruiters to identify pain-points in existing career-guidance
processes.
➢ Problem Decomposition – Requirements were grouped into functional slices (e.g.,
role recommendation, skill-gap detection, quiz engine, resume/report tools, admin
analytics).
➢ Feasibility Study – Compared off-the-shelf LMS/ATS solutions versus a custom
build; a bespoke web app was chosen for finer control, lower recurring cost, and easier
academic deployment.
➢ Technology Stack Finalisation – PHP 8.2 (server logic), Python 3.11 (AI module),
MySQL 8 (relational data), Tailwind CSS 3 (UI layer), mPDF 8 (PDF generation).

5
b) System & Data Design

➢ Layered Architecture:
• “Presentation Layer” (HTML5 + Tailwind + Alpine.js): renders all user/admin
pages, provides dynamic components (quiz timer, progress bar, modals).
• “Application Layer” (PHP): orchestrates user flows, session handling, form
validation, and calls to the AI engine.
• “Intelligence Layer (Python)”: houses hybrid.py, which performs cosine-
similarity scoring between user vectors and job-role vectors, plus rule-based gap
analysis.
• “Data Layer (MySQL + JSON files)”: relational tables for users, logs, and quiz
results; JSON dictionaries for job-role metadata and quiz banks to simplify content
updates.
➢ ER & Sequence Diagrams:

Created with Draw\.io; these map entities such as users, roles, courses, quizzes,
internships, and the activity_log, and illustrate data flow from login through
recommendation, quiz, and admin reporting.

➢ Security & Privacy Blueprint:

Passwords are hashed with Argon2id; prepared statements prevent SQL injection;
activity logs exclude sensitive PII beyond email and name.

6
c) Incremental Development Sprints

Each sprint followed “Plan → Build → Review → Refine”:

Sprint Major Deliverables Key Feedback Incorporated

1 Core user registration & login; Improved UI responsiveness
Tailwind layout skeleton
2 Role-matching API (hybrid.py); Added confidence scores beside roles
dashboard cards
3 Skill-gap matrix & course suggester Based in the user domain and also the
course they completed
4 Quiz engine (one-question flow, Enabled question flagging for later
timer, review)
5 Internship recommender & threshold Allowed admins to tune score
logic thresholds
6 Resume builder & mPDF report Added custom section re-ordering
generator
7 Admin activity log with filters/export Added CSV & PDF export; date-
range filter
8 End-to-end hardening, load tests, Optimised DB indices, enforced
security audit HTTPS

Table 1.1

7
d) Core Algorithms & Modules

➢ Role Recommendation (Python)

➢ Skill Gap Analysis

• Generates a gap table mapping each missing skill to a recommended course,
learning platform link, and estimated completion time.
• Stored in gap_results table for later retrieval by the admin dashboard.
➢ Quiz Engine (PHP)
• Loads a job-role-specific JSON file: data/quizzes/backend_developer.json.
• Stores current question index and remaining time in $_SESSION.
• After submission, writes per-question correctness to quiz_result_detail for
granular analytics.
➢ Internship Recommendation
• hreshold configurable (default 70 %). If met, a query selects internships tagged
with the same job-role ID and high employer rating.
➢ Document Generators
• Resume: Blade-like PHP template → HTML → mPDF → downloadable PDF.
• Project Report: Parses user-entered abstract, objectives, screenshots, and auto-
paginates with 1.5 line spacing, Times New Roman, and automatic
headers/footers.

8
e) Testing & Quality Assurance

Test Type Tools / Process Outcome

Unit Tests PHPUnit (PHP) & PyTest 92% coverage on business logic
(Python)
Integration Postman / Selenium click-paths All APIs return 2xx; quiz flow
stable
Load Apache JMeter (500 virtual users, Avg. response < 220 ms; 0%
5 min) error rate
Security OWASP ZAP passive scan; No critical vulnerabilities
manual SQLi probes detected
UX 12 beta testers (students & 4.6 / 5 satisfaction; minor UI
Acceptance mentors) tweaks applied

Table 1.2

f) Deployment & Maintenance

• Containerisation – The stack ships as a Docker Compose file (php-fpm, nginx,

mysql, python-worker).
• CI/CD Pipeline – GitHub Actions runs linting, tests, and builds images; on main
branch merge it pushes to a private container registry and triggers deployment to
an Ubuntu VPS via SSH.
• Monitoring – Prometheus scrapes Nginx/DB metrics; Grafana dashboards alert on
95th-percentile latency or error spikes.
• Future Enhancements – OAuth 2.0 login, AI-driven adaptive quizzes, and direct
integration with MOOC APIs (Coursera, edX) for auto-enrolment links.

9
1.5 LITERATURE SURVEY:

Recent scholarship on technology-supported career guidance converges on five

complementary streams that underpin our system.

➢ “First, recommender–system research” has progressed from rule-based guidance (e.g.,

Holland-code matching) to data-driven hybrids that blend content- and collaborative-
filtering with graph neural networks; state-of-the-art examples include Skill2Vec’s
embedding of 250 k job ads to suggest roles by cosine similarity of skill vectors \[Li et
al., 2023, ESWA] and the knowledge-graph approach of CareerKG that adds semantic
relations among courses, competencies and occupations \[Aksoy & Hooshyar, 2024,
IEEE Access].

➢ “Second, course-recommendation work” for MOOCs and university catalogs

emphasises closing prerequisite and outcome gaps: EduRank uses learning-to-rank and
sequential patterns to propose “next best” courses based on historical enrolments
\[Chen et al., 2024, LAK], while DeepCourseRec relies on transformer attention over
syllabus text to surface highly granular topics \[Gupta & Verma, 2023, Computers &
Ed.].

➢ “Third, skill-gap analytics” couples labour-market mining with learner profiles;

GapMap aligns ESCO skills with Coursera metadata to quantify proficiency deltas and
visualise personalised road-maps \[Rahman et al., 2022, ICDE], and a more recent
graph-embedding technique projects both users and jobs into a unified latent space to
highlight missing but learnable abilities \[Kaur et al., 2024, WWW].

➢ “Fourth, adaptive assessment” literature shows that quizzes calibrated with Item-
Response-Theory and refined via reinforcement learning improve diagnostic precision
and learner engagement; SmartQuiz shortens test length by 40 % while preserving
reliability \[Zhang & Templin, 2023, AJET], and Job2Quiz dynamically selects
domain-specific questions to predict employability scores \[Singh et al., 2024, CHI].

10
➢ “Fifth, auxiliary modules such as resume builders and activity dashboards” draw on
natural-language-processing advances: BERT-based résumé parsers achieve 94 % F1
in entity extraction \[Ahmad et al., 2024, COLING], and privacy-aware learning
analytics dashboards like TrackX log click-streams, dwell-time and resource utilisation
to support administrators’ interventions \[Morgan & Kou, 2023, JLA]. Collectively,
this body of work motivates our integrated Career Recommendation System: we adopt
hybrid embeddings for role matching, skill-gap visualisation for targeted course advice,
IRT-driven adaptive quizzes to trigger internship suggestions above a performance
threshold, BERT-assisted résumé generation, and a fine-grained activity logger to close
the feedback loop between learners, content and career outcomes.

11
 CHAPTER 2: SYSTEM DESIGN AND IMPLEMENTATION

System Design and Implementation focuses on the structural and functional design of the
Career Recommendation System. It outlines the system architecture and key components,
specifying how different modules interact to provide personalized career suggestions. The
chapter also includes the system requirement specifications, detailing the hardware and
software prerequisites for smooth functioning. Additionally, it presents the user interface
design, showcasing the layout and navigation structure tailored for an intuitive user
experience. Finally, this chapter covers essential design models such as the Entity-
Relationship (ER) diagram and Data Flow Diagrams (DFDs), which visually represent data
storage, relationships, and the flow of information throughout the system.

2.1 SYSTEM ARCHITECTURE AND COMPONENTS:

The system architecture of the Career Recommendation System is designed to ensure

seamless interaction between users and the backend intelligence that powers
recommendations, quizzes, course analysis, and resume/report generation. The architecture
follows a modular, layered approach, separating concerns such as data handling, business
logic, and user interaction. This structure enhances maintainability, scalability, and
performance of the overall system.

1) System Architecture Overview

The architecture can be broadly categorized into the following tiers:

• Presentation Layer (Front-end)

• Application Layer (Back-end Logic)
• Database Layer (Data Storage)
• External Tools Integration Layer

12
2) Components of the System

A. Presentation Layer

• Built using HTML, CSS (Tailwind CSS), JavaScript, and PHP.

• Displays dynamic content such as:
o Recommended career roles
o Course gap analysis
o Quizzes (one question per page with timer)
o Resume builder and report generator
• Features user-friendly UI with interactive buttons, toggle views, and form
validation.

B. Application Layer

• Written in PHP and Python (for intelligent recommendations).

• Responsible for:
o Processing user inputs (interests, completed courses)
o Interfacing with the Python script (hybrid.py) to generate career suggestions
using hybrid matching logic
o Managing user sessions and quiz navigation logic
o Scoring quizzes and providing detailed feedback
o PDF generation using mPDF library for resumes and reports
• Acts as the bridge between the front-end and database.

C. Database Layer

• Uses MySQL for structured data storage.

• Major tables include:
o users: Stores user registration, login details, and activities
• Ensures data integrity, indexing for faster access, and security (hashed passwords).

13
D. External Tools Integration

• Python Script (hybrid.py): Calculates best-fit job roles using a hybrid approach
(interest + completed course match).
• mPDF Library: Used to generate formal PDFs for:
o User resumes
o Project reports with Times New Roman font, 1.5 spacing, and proper formatting
• JavaScript Enhancements:
o Real-time quiz timer
o View password toggle
o Dynamic form behaviour

3) Workflow of the System

• User Registration/Login: The user creates an account or logs in using credentials.
Features like "View Password" and "Forgot Password" enhance usability.
• Input Gathering: Users enter interests and completed courses.
• Recommendation Generation: PHP sends data to hybrid.py, which processes and
returns job role suggestions.
• Job Role Display: Suggested roles are shown as buttons. Clicking on them shows
course gaps and the option to take a domain-specific quiz.
• Quiz System:
o Loads questions from a JSON file
o Tracks answers across multiple pages
o Uses session variables to store progress
o Provides feedback with score
o Shows internship options if the score exceeds a threshold

14
 • Resume & Report Generator:
o Collects user input in form fields
o Generates and downloads a professional PDF file using mPDF
• Admin Monitoring:
o Admin panel tracks login times, visited pages, quiz attempts, and more.

4) Key Benefits of the Architecture

• Separation of Concerns: Clean division between UI, logic, and data.
• Modularity: Easy to update or replace individual components.
• Security: Data validation, hashed passwords, session-based quiz handling.
• Performance: Optimized SQL queries and cached data retrieval.

15
2.2 SYSTEM REQUIREMENT SPECIFICATIONS:

System Requirement Specifications (SRS) describe all necessary technical and functional
needs to design, develop, and deploy the Career Recommendation System successfully.
This includes hardware and software requirements, functional requirements, non-
functional requirements, and user-specific requirements. A well-defined SRS ensures the
system operates reliably, is user-friendly, and meets all project goals.

1) Hardware Requirements

These define the minimum and recommended specifications for servers and client devices
to run the system efficiently.

Recommended
Component Minimum Requirement
Requirement
Quad Core 2.5 GHz or
Processor Dual Core 2.0 GHz
higher
RAM 4 GB 8 GB or more
Storage 250 GB HDD 500 GB SSD
Display 1024×768 resolution 1366×768 or higher
High-speed (5 Mbps or
Internet Basic broadband (1 Mbps)
more)
Browser Chrome, Firefox, or Edge Latest version of Chrome

Table 1.3

16
2) Software Requirements

These specify the software stack needed for both development and deployment.

➢ Server-Side:
• Operating System: Windows / Linux (Ubuntu)
• Web Server: Apache (XAMPP/LAMP/WAMP stack)
• Server Language: PHP 7.4+ (for backend logic)
• Database: MySQL
• Python: Python 3.8+ (for role matching logic using hybrid.py)
• PDF Generator: mPDF library for PHP

➢ Client-Side:
• Languages: HTML5, CSS3, JavaScript
• Frameworks/Libraries:
• Tailwind CSS for styling
• jQuery (for simple client-side interactivity)
• AJAX (for dynamic data updates)

17
3) Functional Requirements

These outline what the system must do to achieve its purpose.

Requirement ID Description
User registration and login with "View
FR1 Password" and "Forgot Password"
features
Accept user inputs (interests and
FR2
completed courses)
Generate career recommendations using a
FR3
hybrid Python script
Display course gap analysis for each
FR4
recommended job role
Conduct domain-specific quizzes (1
FR5
question per page, with timer)
Evaluate quiz and show result with
FR6
feedback
FR7 Show internships if score > threshold
Allow user to generate and download
FR8
resume (PDF)
Allow user to generate and download
FR9
project report (PDF)
Admin can monitor user activities (logins,
FR10
quizzes, visits)

Table 1.4

18
4) Non-Functional Requirements

These define the quality attributes and performance expectations.

Category Requirement
Usability The interface must be intuitive and mobile-responsive.
Response time for generating results should be under 3
Performance
seconds.
Passwords must be hashed and data should be
Security
validated on both client and server sides.
The system should support multiple users
Scalability
simultaneously without performance degradation.
Code should follow modular practices for easier
Maintainability
updates.
Availability The system should be available 99% of the time.

Table 1.5

19
5) User Requirements

The system should accommodate three primary types of users:

➢ Student/User
• Register/login to system
• Input interests and completed courses
• View recommendations and quizzes
• Download resume and report
➢ Admin
• Monitor user activity logs
• Manage quiz data and role mappings
• View system usage analytics
➢ System
• Auto-score quizzes
• Generate accurate career suggestions
• Securely store and retrieve data

6) Data Requirements
• Input Data: Interests, courses completed, quiz answers
• Output Data: Suggested job roles, quiz results, course gap report, resume and
project PDFs
• Stored Data: User profiles, course lists, quiz questions, activity logs

In summary, the System Requirement Specifications provide a comprehensive blueprint to

ensure the Career Recommendation System functions as intended. It defines the
environment in which the system operates, how it behaves, and what constraints it must
adhere to, forming the foundation for development and quality assurance.

20
2.3 USER INTERFACE DESIGN:

The User Interface (UI) Design of the Career Recommendation System plays a crucial role
in delivering a seamless, intuitive, and engaging experience to users. It is crafted to be
simple, responsive, and interactive, enabling users to easily navigate through different
features like career recommendations, course gap analysis, quizzes, resume generation, and
project report downloads.

1) Design Principles Followed

The interface has been developed using HTML5, Tailwind CSS, and JavaScript,
incorporating the following key UI design principles:

• Simplicity: The layout is clean and uncluttered with easy-to-read fonts and
appropriate spacing.
• Consistency: Uniform styling, colours, and button designs are used across all
pages.
• Responsiveness: The UI adapts smoothly to different screen sizes (desktop, tablet,
mobile).
• User-Centered: All elements are placed for maximum usability and minimal user
effort.

2) Major UI Screens and Features

A. Homepage / Landing Page
• Welcoming design with the system’s name and tagline.
• Navigation buttons like "Start Now", "Register", and "Login".
• Brief introduction and image/banner to create visual appeal.

21
22
B. Registration and Login Pages
• Fields for email, password, and confirm password (with password visibility
toggle).
• Forgot Password link to reset credentials via email or security questions.
• Validation prompts for incorrect or empty fields.
• Success and error messages shown using styled alert boxes.

23
C. Career Recommendation Page
• Input forms for:
o Selecting interests (dropdown/multiselect)
o Selecting completed courses (checkbox list or multiselect)
• Submit button triggers backend processing via PHP → Python.
• Recommended careers displayed as clickable buttons with brief job role
descriptions.

24
D. Job Details and Course Gap Page
• When a career role is clicked:
o Display a list of required vs. completed courses.
o Show a "Take Quiz" button to test knowledge in the chosen domain.
• Color-coded course list (e.g., green for completed, red for missing).

25
E. Quiz Interface
• One question per page format.
• Includes:
o Question text with multiple-choice options
o Next, Previous, and Submit buttons
o Timer at the top of the page
o Highlight for unanswered questions
• After submission:
o Display of results with
o indicators
o Final score and feedback message
o Internship suggestions if score is high enough

26
27
28
F. Resume Builder UI
• Form to enter:
o Personal information
o Education
o Skills
o Projects
o Work experience (optional)
• Submit button generates a professional PDF resume using mPDF with options to
download.

29
G. Project Report Generator
• Minimal form where user enters project name, abstract, features, etc.
• On submit, generates a multi-page formal project report with:
o Times New Roman font
o 1.5 line spacing
o Automatic page breaks and numbering

30
31
H. Admin Panel UI
• Login-only access
• Dashboard shows:
o User statistics (logins, quiz attempts, downloads)
o Table view for activity logs
o To view email, quiz questions, courses, internship and company
o To filter the data based on email, newest and oldest first format.

32
I. Internship & Company
• Recommendations are tailored to the user’s selected job role and domain
knowledge.
• Each internship includes:
o Role description
o Duration
o Location links
• Users receive suggestions for leading companies in their chosen field.
• Helping them gain practical experience and prepare for their careers.

33
3) Design Technologies and Tools
• Tailwind CSS: Used for rapid, responsive UI development with utility-first classes.
• JavaScript + jQuery: Handles client-side validation, dynamic form behavior, and
timer functions.
• AJAX: Used for loading data without reloading pages (e.g., quiz content).
• Font Awesome/Icons: Used for buttons and navigation aesthetics.

4) Accessibility Features
• Keyboard navigable forms and buttons
• Clear font contrast and size for readability
• Error messages and form validation for guiding users

5) Sample UI Elements

Element Design
Rounded, shadowed, hover-animated
Buttons
using Tailwind
Full-width, neatly spaced with labels and
Forms
placeholders
Used for role suggestions and dashboard
Cards
options
Navbar/Footer Consistent design with site logo and links

Table 1.6

34
6) Navigation Flow

[Home Page]

[Login/Register]

[User Dashboard]

[Enter Interests & Courses] → [Get Career Suggestions] → [View Job Details & Course
Gaps]

[Take Quiz] → [Result + Internships]

[Generate Resume / Report]

35
2.4 ER DIAGRAM AND DATA FLOW DIAGRAMS (DFDS):

This section focuses on the data modelling and process flow representation of the Career
Recommendation System. These diagrams help visualize how data is structured (ER
Diagram) and how it moves through the system (DFDs). These models are essential for
both system design and implementation.

➢ Entity-Relationship (ER) Diagram

The ER Diagram defines the entities in the system and the relationships between them. It
is a blueprint of the database structure, ensuring proper data storage and retrieval.

Main Entities and Relationships:

Figure 1.1

36
➢ Data Flow Diagrams (DFDs)

DFDs show how data moves through the system at different abstraction levels.

2.5

Figure 1.2

37
1. User Registration and Admin Module

Figure 1.3

38
2. Career Recommendation Module

Figure 1.4

39
3. Job Details And Course Gap Analysis Module

Figure 1.5

40
4. Quiz System Module

Figure 1.6

41
5. Internship Finder Module

Figure 1.7

42
6. Resume Builder Model

Figure 1.8

43
7. Project Report Generator Model

Figure 1.9

44
8. Admin dashboard Module

Figure 2.0

45
9. User Activity Logging Module

Figure 2.1

46
2.5 IMPLEMENTATION DETAILS:

The implementation strategy outlines how the Career Recommendation System is

developed, integrated, tested, and deployed. It focuses on converting the design into a fully
functional web-based application that provides personalized career guidance, skill-gap
analysis, interactive quizzes, resume/report generation, and admin monitoring. The
strategy involves a modular and step-wise development approach, ensuring that each
component works independently and integrates smoothly into the full system.

1) Technology Stack Used

Layer Technology
HTML5, Tailwind CSS, JavaScript,
Frontend
jQuery
Backend PHP 7.4+, Python 3.8+
Database MySQL / MariaDB
PDF Generation mPDF (for resume and report PDFs)
Web Server Apache (XAMPP/LAMP/WAMP)
Hosting Localhost / Web Hosting Server

Table 1.7

2) Modular Implementation Plan

The system was implemented in logical modules to ensure proper separation of concerns
and smooth integration. Below are the main implementation modules:

47
Module 1: User Authentication

• Files: register.php, login.php, forgot_password.php

• Features:
o Secure registration with form validation
o Password visibility toggle
o Forgot password reset functionality
o Session management for logged-in users
• Security: Passwords are stored using password_hash() and verified with
password_verify().

Module 2: User Input & Career Recommendation

• Files: input.php, hybrid.py, recommendations.php

• Process:
o Users input their interests and completed courses
o Data is passed to a Python script (hybrid.py)
o The script uses a hybrid matching algorithm to generate suitable job roles
o Results are displayed as clickable role buttons

Module 3: Course Gap Analysis

• Files: job_details.php
• Functionality:
o On selecting a job role, the system compares the role’s required courses with user’s
completed ones
o Shows a list of missing courses and recommendations to learn them
o “Take Quiz” button initiates the domain quiz

48
Module 4: Domain-Specific Quiz System

• Files: quiz.php, result.php

• Features:
o Questions loaded dynamically from JSON file based on job role
o One question per page with navigation buttons (Next/Previous)
o Timer for quiz duration
o Results shown with (correct) and (wrong) indicators
o Quiz result stored in the database
o If score ≥ threshold, internship options are shown

Module 5: Resume Builder

• Files: resume_builder.php, generate_resume.php

• Process:
o User enters education, skills, projects, and personal info
o mPDF is used to generate a formal, downloadable PDF resume
o Designed in a clean professional layout, printable on A4

Module 6: Project Report Generator

• Files: project_report_form.php, generate_report.php

• Features:
o Users input project title, abstract, features, technologies
o mPDF creates a multi-page, Times New Roman, 1.5 spaced report
o Auto page numbering and section formatting included

49
Module 7: Admin Panel & User Monitoring

• Files: admin_login.php, admin_dashboard.php, view_logs.php

• Capabilities:
❖ Admin can view:
o User login times
o Quizzes taken
o Pages visited
o Resume and report downloads
• Real-time activity tracking improves system oversight

3) Integration Strategy
• Step 1: Backend PHP files were integrated with the frontend forms and buttons
using POST/GET methods.
• Step 2: Python script was executed using shell_exec() or exec() in PHP, with data
passed via JSON or command-line arguments.
• Step 3: Session variables were used to maintain user state and data (e.g., selected
quiz, interests).
• Step 4: Dynamic content (e.g., recommended roles, quiz questions) was loaded
using AJAX where needed.

4) Testing During Implementation

• Unit Testing: Each PHP and Python script was tested independently with various
inputs.
• Integration Testing: Ensured smooth flow from one module to another, especially
from:
o Input → Python → PHP
o Quiz → Result → Internship

50
 • User Testing: Feedback was collected from a few users to enhance usability and
fix bugs.
• Security Testing: Input validation and SQL injection prevention using prepared
statements.

5) Deployment Strategy
• Local Testing: Fully tested on localhost (XAMPP).
• Deployment: Uploaded to a web hosting server with PHP and MySQL support.
• Database Migration: Exported and imported via phpMyAdmin.
• Backup: Periodic backups configured for database and uploaded files.

6) Challenges Faced and Solutions

Challenge Solution
Used shell_exec() and JSON to bridge
Integrating Python with PHP
data
Maintaining quiz session state Implemented $_SESSION tracking
Used mPDF with advanced styling and
Formatting multi-page reports
page break control
Handling responsive design Tailwind CSS used for adaptive layouts

Table 1.8

51
❖ Waterfall Model for Career Recommendation System

1. Requirements Gathering and Analysis

In this phase, all requirements for the system are collected and analyzed thoroughly.

➢ Activities:
• Identify the need for a career recommendation platform.
• Gather requirements for:
o User registration & login
o Interest and course selection
o Career role suggestions
o Course gap analysis
o Quiz system with scoring
o Resume & project report generation
o Admin monitoring module

➢ Deliverables:
• Software Requirement Specification (SRS) Document
• List of features and functional requirements

2. System Design

Based on the SRS, the system's architecture, components, and data flow are designed.

➢ Activities:
• Create the ER Diagram and Data Flow Diagrams (DFDs)
• Design system architecture (Frontend, Backend, Database)
• Plan UI layout (Homepage, Dashboard, Forms, Quiz)
• Choose tech stack (PHP, Python, MySQL, Tailwind CSS, mPDF)

52
➢ Deliverables:
• System Architecture Design
• Database Schema
• UI Mockups and Layout Plan
• Design documents for each module

3. Implementation (Coding)

This is the development phase where the actual system is built according to the design.

➢ Activities:
• Develop user authentication system
• Implement input forms and role recommendation via Python
• Build course gap analysis module
• Create quiz system with timer, score tracking, and feedback
• Integrate resume and report PDF generation using mPDF
• Build admin panel for tracking user activities

➢ Deliverables:
• Fully functional PHP and Python codebase
• Integrated modules working end-to-end
• Responsive frontend with Tailwind CSS

53
4. Testing

All modules and the full system are tested to ensure functionality and correctness.

➢ Activities:
• Unit Testing of PHP, Python, and JavaScript components
• Integration Testing between modules (PHP ↔ Python, quiz ↔ results)
• UI Testing for responsiveness and usability
• Database Testing to validate data operations
• Security Testing for login and data handling

➢ Deliverables:
• Test cases and test reports
• Bug fixes and improvements
• Final tested version of the system

5. Deployment

The fully tested system is deployed for actual use, either on a local or web server.

➢ Activities:
• Set up web hosting with PHP and MySQL support
• Migrate the database using phpMyAdmin
• Upload all project files to the server
• Perform final live testing
• Ensure mPDF and Python script integrations work on server
➢ Deliverables:
• Live working project hosted on web server
• Access for users and admin
• Backup and recovery setup

54
6. Maintenance

After deployment, the system is maintained for updates, bug fixes, and enhancements.

➢ Activities:
• Monitor user activities and logs
• Collect feedback for improvements
• Fix reported issues (if any)
• Add new features (optional: email alerts, analytics)

➢ Deliverables:
• Maintenance logs
• Updated versions (if applicable)
• User satisfaction reports

55
 CHAPTER 3: CODE SNIPPET AND TESTING

This chapter presents key source code snippets and the testing strategies employed in the
development of the Career Recommendation System. It includes critical sections of code
written in PHP, Python, HTML, and JavaScript that implement core functionalities such as
user registration, interest-based job role recommendations, course gap analysis, domain-
specific quizzes, resume and project report generation, and admin activity tracking.
Alongside the code, this chapter also highlights the testing procedures carried out at various
levels including unit testing, integration testing, and user interface testing. The results
demonstrate the system’s correctness, responsiveness, and reliability across all modules.

3.1 MODULES EXPLANATION WITH SCREENSHOTS OF PROJECTS:

➢ Home Page
• The homepage of “Career Nest”, featuring its unique logo and a sleek purple-to-
pink gradient theme, offers a warm and professional introduction to the platform.
The brand name "Career Nest" is prominently displayed, symbolizing a safe and
supportive space where users can begin building their future. With its clean layout
and visually appealing design, the homepage immediately captures attention,
reinforcing the platform's identity as a trusted starting point for personalized career
growth and exploration.

56
• The homepage of “Career Nest” features a simple and elegant header showcasing
only the brand name and logo, creating a clean and focused first impression.
Positioned prominently at the top, there are navigation links: Features, About, and
a Login button styled in purple with white text.

• Key features of “Career Nest” offers a powerful set of tools to support every stage
of a user’s career journey. The “Career Matching” feature recommends job roles
tailored to a user’s interests and completed courses, helping them discover suitable
career paths. to help users present themselves professionally, “Career Nest”
includes a customizable “Resume Builder” and a formal “Project Report
Generator”, making it easy to create polished, structured documents for job and
academic purposes.

57
➢ Login Page

• The “Register” page in “Career Nest” allows new users to create an account and
begin their personalized career journey. With a clean, user-friendly design
matching the platform’s purple-to-pink gradient theme, the registration form
collects essential details such as name, email, and password. It includes form
validation to ensure data accuracy and a “View Password” toggle for convenience.
Once registered, users gain full access to features like career matching, skill
insights, quizzes, internship recommendations, and tools like the resume and
project report builder.

• The “Reset Password” feature in “Career Nest” ensures account security while
providing a smooth recovery process for users who forget their login credentials.
Accessible from the login page via the “Forgot Password” link, it allows users to
enter their registered email address and receive a secure reset link or a temporary
password. This feature is designed to be quick, user-friendly, and safe—enabling
users to regain access to their accounts without compromising security. It helps
maintain continuous access to all platform features, ensuring that users can return
to their career journey without interruption.

58
➢ User Input

• The User Input feature in the Career Recommendation System allows individuals
to enter their domain of interest and list the courses they have already completed.
This input forms the basis for personalized recommendations, enabling the system
to identify suitable job roles, highlight missing courses, and generate relevant
quizzes, resumes, and project reports tailored to the user's profile.

59
➢ Recommends Missing Courses

• The “Missing Courses” feature in “Career Nest” plays a crucial role in bridging the
gap between a user’s current knowledge and their desired career path. After
selecting a domain and completed courses, the system analyses the user’s inputs
and recommends job roles. For each recommended role, it identifies the courses the
user hasn’t yet completed but are essential for that role. These missing courses are
displayed clearly, helping users understand exactly what they need to learn next.
This targeted guidance ensures users can upskill efficiently and stay on track toward
achieving their career goals.

60
➢ Quiz Module

• Domain-Specific Quizzes: Each quiz is tailored to a specific job role or domain

(e.g., Web Development, Data Science).
• One Question Per Page: Clean, focused interface that shows one question at a time
with navigation buttons.
• Built-in Timer: Each quiz session includes a countdown timer to encourage time
management.
• Detailed Feedback: After submission, results display correct and incorrect
answers with indicators.
• Score-Based Outcome: If a user scores above a set threshold (e.g., 7/10), they
unlock internship recommendations.

61
• Session Tracking: Questions are stored in the session to maintain consistency
across navigation.
• Unanswered Question Alerts: Highlights questions left unanswered before
submission.
• JSON-Based Questions: Quiz questions are dynamically loaded from a structured
JSON file for easy updates.
• Secure Evaluation: All answers are validated securely on the server before
results are shown.

62
63
64
➢ Internships & Company Recommendation

• “Career Nest” enhances career readiness with smart “Internship and Company
Recommendations” tailored to each user’s skills and quiz performance. Based on
the user’s selected job role and domain knowledge, the platform suggests relevant
internship opportunities that align with their goals. Each internship listing includes
detailed information about the role, required skills, and application links.
Additionally, “Career Nest” recommends top companies in the chosen field, giving
users a clearer picture of where their career path can lead.

65
➢ Admin

• The Admin Module in the Career Recommendation System serves as the central
management and monitoring hub for overseeing user interactions, system usage,
and engagement analytics. It is designed to provide administrators with a complete
and real-time overview of how users are interacting with various components of
the platform
• Tracks user login/logout time.
• Records selected domain and completed courses.
• Logs job roles clicked by the user.
• Tracks course visits only if user stays for 5+ seconds.
• Monitors quiz attempts with topic, score, and time taken.
• Logs internship and company links viewed (after 5+ seconds).
• Tracks usage of résumé builder.
• Tracks usage of project report generator.
• Displays all data in a clean, visual admin dashboard.
• Helps identify active and inactive users.
• Enables data-driven decisions for mentoring and improvement.

66
67
➢ Resume

• The “Resume Builder” in Career Nest is a powerful tool that helps users create a
professional, well-structured resume with ease. Designed for simplicity and
accessibility, it allows users to input their personal details, education, skills,
projects, and experiences through a guided form. Users can also add multiple
educational qualifications or project entries using the “Add More Rows” feature.
Once completed, the resume is automatically formatted into a clean, professional
layout and can be downloaded as a PDF from any device. This feature ensures users
have a polished, job-ready resume tailored to showcase their strengths and career
aspirations effectively.

68
➢ REPORT

• The Report Builder in the Career Recommendation System enables users to

generate a formal, multi-section project report by entering structured data such as
student details, abstract, and chapter content. Using mPDF, it formats the input into
a professional PDF document with Times New Roman font, 1.5 line spacing,
automatic page numbers, and clearly defined sections, making it suitable for
academic or institutional submission.

69
70
3.2 CODE:

➢ Home Page code

71
➢ Login Page Code

72
➢ Course & Interest Input

❖ Dataset

73
➢ Career Recommendation Engine

74
75
❖ Dataset

➢ Quiz code

76
77
➢ internship and company

❖ Internship Dataset

78
❖ Company Dataset

79
➢ Admin

80
81
➢ Resume

82
83
➢ Report

84
3.3 TESTING RESULTS:

The Career Recommendation System underwent comprehensive testing to ensure its

reliability, functionality, and user-friendliness. Various test cases were executed across all
modules including user registration, login, career role recommendation, course gap
analysis, quiz system, PDF generation, and admin monitoring. Each module was tested for
valid and invalid inputs, proper error handling, UI responsiveness, and data accuracy. All
functionalities performed as expected, with successful validation of user workflows and
secure operations. The system passed all unit and integration test cases, confirming its
readiness for deployment.

➢ Here is your test case information neatly formatted as a table:

Test
Test Expected Actual Statu
Case Module Tested Input
Description Output Output s
ID

Works as
Validate Valid Registratio
expected,
TC0 User successful name, n success,
redirects
1 Registration user email, redirect to Pass
after
registration password login page
success

Check login Correct Redirects

TC0 Redirect to
User Login with valid email and to
2 dashboard Pass
credentials password dashboard

Displays
Check login
TC0 Wrong Show error “Invalid
User Login with invalid
3 password message credentials Pass
credentials
” message

85
 Show
Test input Validation
TC0 Interest & Blank validation
form works
4 Course Input fields error Pass
validation properly
messages

Check
Role
Role correct roles Interests + List of
TC0 suggestion
Recommendati are Complete matching
5 s displayed Pass
on (Python) recommende d courses job roles
correctly
d

Test missing Show Course

TC0 Course Gap course Selected completed gaps
6 Analysis detection for role vs missing shown Pass
selected role courses accurately

Verify quiz Questions

Quiz key / Questions
TC0 questions with
Quiz Loading role load per
7 load options Pass
selected page
correctly displayed

Score
Show
Test answer calculated
TC0 Quiz Quiz score with
evaluation and
8 Submission answers / Pass
and scoring feedback
feedback
shown

PDF
Generate
Personal, Formatted generated
TC0 Resume downloadabl
education, PDF and
9 Generation e resume Pass
skills info resume file downloade
PDF
d

86
 Generate A4, Times PDF
formal Report New generated
TC1 Project Report
multi-page content Roman, with
0 Generation Pass
project via form 1.5 spaced correct
report PDF formatting

Admin Admin
Track and sees logs panel
User
TC1 Admin Activity display user of login displays
interaction
1 Monitoring login and time, full Pass
s
quiz activity quizzes, activity
views history

Prevent SQL Input

Special SQL
TC1 Security injection in sanitizatio
characters Injection
2 Testing login/registe n and Pass
in input blocked
r forms rejection

Responsiv
Check UI on Various Layout
TC1 Responsive e across all
mobile and screen adjusts to
3 Design tested Pass
desktop sizes screen size
devices

Table 1.9

87
 CHAPTER 4: CONCLUSION AND FUTURE ENHANCEMENTS

This chapter provides a comprehensive wrap-up of the Career Recommendation System

project, summarizing its objectives, the methodology used, and key outcomes achieved. It
highlights the significance and real-world impact of the project in guiding users toward
suitable career paths based on their interests and completed courses. The chapter also
acknowledges certain limitations encountered during development, such as the scope of
quiz content or system scalability. Lastly, it outlines future enhancement possibilities,
including the integration of AI-based resume scoring, real-time job alerts, mobile app
version, and multilingual support, to further improve the system’s usability, intelligence,
and reach.

4.1 SUMMARY OF THE PROJECT’S OBJECTIVES, METHODOLOGY, AND

KEY FINDINGS:

The Career Recommendation System was developed with the aim of providing
personalized career guidance to users based on their interests and academic background.
The project combined a structured methodology and modern technologies to design a user-
friendly platform that offers career suggestions, identifies skill gaps, and supports users in
building professional documents like resumes and project reports. Through an interactive
web interface, the system ensures that users receive relevant career options, supporting
learning resources, and an evaluation mechanism through quizzes. The project not only
meets its intended goals but also opens up possibilities for further enhancements and real-
world application.

88
➢ Objectives
• To recommend suitable job roles based on user interests and completed courses.
• To identify missing skills or knowledge areas through course gap analysis.
• To evaluate users’ domain knowledge via interactive quizzes.
• To provide downloadable professional tools like resumes and project reports.
• To enable admin monitoring of user activities for insights and improvements.

➢ Methodology
• Used a hybrid algorithm in Python for career role recommendation.
• Implemented a modular architecture using PHP, MySQL, and Tailwind CSS.
• Integrated Python with PHP for backend processing.
• Used mPDF for generating formal PDF documents (resume, report).
• Followed the Waterfall Model for systematic development and testing.

➢ Key Findings
• The system effectively recommends careers and highlights course gaps.
• Users can assess their knowledge through quizzes and receive feedback.
• Resume and report generation features are accurate and professional.
• The admin panel offers valuable insights into user interactions.
• The project demonstrates practical use of technology for real-world career
guidance.

89
4.2 CONTRIBUTION AND SIGNIFICANCE OF THE PROJECT:

The Career Recommendation System makes a meaningful contribution to the field of

educational technology by bridging the gap between academic learning and career
planning. In today’s competitive environment, students and job seekers often struggle to
choose a career path aligned with their interests and skills. This system provides an
intelligent solution that helps users make informed decisions by analysing their preferences
and learning history.

Major Contributions:

➢ Personalized Career Guidance:

• The system tailors job role suggestions for each user based on their interests and
completed courses, offering a customized path rather than generic advice.

➢ Skill Gap Identification:

• It clearly shows which relevant courses a user is missing for a selected job role,
encouraging continuous learning and skill development.

➢ Interactive Learning Evaluation:

• The domain-specific quiz system allows users to self-assess their readiness for a
role, providing immediate feedback with correct/incorrect indicators.

➢ Document Automation:
• Users can generate professional-quality resumes and structured project reports in
PDF format, eliminating the need for external tools.

90
➢ Admin Monitoring & Analytics:
• The admin panel logs and tracks user activity like login time, quizzes attempted,
roles viewed, and courses explored, supporting better platform management and
insights.

Significance of the Project:

➢ Empowering Users:
• By guiding users in selecting the right career and showing them the steps to get
there, the system empowers individuals to take control of their future.

➢ Educational Support Tool:

• It serves as a supplementary platform for students and academic institutions to
support career counselling and planning.

➢ Scalable and Extendable:

• The modular design makes it easy to add new roles, quizzes, and features, making
the system suitable for long-term use and large-scale deployment.

➢ Promotes Skill Development:

• By showing the course gaps and encouraging quiz participation, the system
naturally promotes learning and preparation for real-world roles.

91
4.3 LIMITATIONS:

While the Career Recommendation System successfully delivers personalized job role
suggestions, skill gap analysis, and professional document generation, it also has certain
limitations that may affect its scalability, adaptability, and user experience in broader
contexts. Identifying these limitations is essential for understanding the boundaries of the
current system and planning future improvements.

Identified Limitations:

➢ Limited Data Scope

• The system’s recommendations are currently based on a predefined set of job roles,
courses, and quiz questions. This limits the diversity and depth of suggestions it
can provide. Users interested in less common or emerging careers may not find
relevant options in the system.

➢ Static Quiz Content

• The quizzes associated with each role are stored in JSON files and manually
created. This makes the quiz system less dynamic and prevents real-time updates
or the addition of adaptive learning content based on user performance.

➢ No Real-Time Industry Integration

• The system does not fetch or display real-time job openings, industry trends, or
internship opportunities directly from external APIs or job portals, which could
make it more useful and up-to-date.

➢ Basic AI Logic
• Although the system uses a hybrid approach for role matching, the logic remains
rule-based and lacks advanced machine learning or AI capabilities for deeper
analysis and prediction.

92
➢ No Multi-Language Support
• The platform is currently designed for English-speaking users only. Non-English
speakers or those from different educational systems may find it less accessible.

➢ User Personalization is Limited

• The recommendations do not yet adapt based on user behaviour over time (e.g.,
course completion progress, quiz performance history, etc.), which could help
refine suggestions more effectively.

➢ Mobile Responsiveness Can Be Improved

• While the UI is built with responsiveness in mind, certain features like PDF preview or
detailed quiz feedback may not be fully optimized for smaller mobile screens.

93
4.4 FUTURE ENHANCEMENTS:

To increase the effectiveness, scalability, and user satisfaction of the Career

Recommendation System, several future enhancements can be implemented. These
enhancements aim to address the current limitations and expand the system’s capabilities
to serve a wider audience with greater accuracy, personalization, and usability.

➢ Integration with Real-Time Job Portals and Internships

• Connect the system with APIs from job platforms like LinkedIn, Indeed, or
Internshala.
• Display live job openings and internship opportunities relevant to the recommended
roles.

➢ AI-Based Role Prediction

• Use machine learning models to analyse user behaviour, preferences, quiz scores,
and academic performance for more intelligent and adaptive career suggestions.
• Improve personalization by learning from historical user data.

➢ Dynamic Quiz and Learning Paths

• Replace static quizzes with a question bank that dynamically generates questions.
• Introduce adaptive learning paths based on user performance to guide them step-
by-step.

➢ Mobile App Development

• Build a cross-platform mobile app to make the system more accessible and user-
friendly on smartphones and tablets.

➢ Multilingual Support
• Add language translation features to support users from different regions and
educational backgrounds.

94
➢ Smart Resume Enhancements
• Add AI-powered resume scoring and keyword optimization to help users tailor their
resumes for specific job roles.

➢ Integration with E-Learning Platforms

• Recommend courses from platforms like Coursera, Udemy, or edX based on
identified skill gaps.
• Provide direct links to enroll and track progress.

➢ Mentor or Chatbot Assistance

• Introduce a chatbot to guide users through the system and answer questions.

• Add a mentor module where users can get feedback from real professionals.

95
 REFERENCE

1) Y. Li, X. Zhao, and H. Wang, “Skill2Vec: Embedding job postings for role
recommendation using hybrid similarity metrics,” Expert Systems with
Applications, vol. 228, 2023. doi: 10.1016/j.eswa.2023.120918.
2) S. Aksoy and D. Hooshyar, “CareerKG: A Knowledge Graph Approach to Career
Path Recommendation,” IEEE Access, vol. 12, pp. 45678–45692, 2024. doi:
10.1109/ACCESS.2024.3345678.
3) L. Chen, Y. Lin, and M. Tan, “EduRank: Learning-to-Rank Framework for
University Course Recommendations,” in Proc. 14th Int. Conf. on Learning
Analytics & Knowledge (LAK), Kyoto, Japan, 2024, pp. 234–243.
4) R. Gupta and P. Verma, “DeepCourseRec: Transformer-Based Course
Recommendation Using Syllabus Semantics,” Computers & Education, vol. 207,
2023. doi: 10.1016/j.compedu.2023.104606.
5) T. Rahman, S. Das, and A. Sengupta, “GapMap: Visual Skill-Gap Analysis for
Lifelong Learning,” in Proc. IEEE Int. Conf. on Distance Education (ICDE), 2022,
pp. 92–101.
6) G. Kaur, A. Mehta, and V. Raj, “Latent Skill Projections for Personalized Career
Pathways,” in Proc. World Wide Web Conf. (WWW), Singapore, 2024, pp. 1193–
1204. doi: 10.1145 (placeholder for actual DOI).
7) X. Zhang and J. Templin, “SmartQuiz: Adaptive Testing Using IRT and
Reinforcement Learning,” Australasian Journal of Educational Technology
(AJET), vol. 39, no. 1, pp. 56–74, 2023.
8) R. Singh, M. Bhatt, and A. Ghosh, “Job2Quiz: A Dynamic Assessment System for
Employability Prediction,” in Proc. ACM Conf. on Human Factors in Computing
Systems (CHI), Honolulu, HI, 2024.
9) M. Ahmad, F. Rahimi, and K. Cho, “BERT-Enhanced Resume Parsing for HR
Applications,” in Proc. Int. Conf. on Computational Linguistics (COLING), 2024,
pp. 1120–1131.
10) C. Morgan and L. Kou, “TrackX: Privacy-Aware Analytics for Learning
Platforms,” Journal of Learning Analytics (JLA), vol. 10, no. 3, pp. 44–60, 2023.
doi: 10.18608/jla.2023.7419.

96