DEPARTMENT OF MATHEMATICS &

COMPUTER SCIENCE PROPOSAL

DEFENSE 2024/2025

Crafting Career Pathways: A Recommender

System Approach

NAME: YESUFU ISAIAH AKINNINUOLUWA

MATRIC NUMBER: EU210102-2579
DEPARTMENT: COMPUTER SCIENCE
SUPERVISOR: DR. B. ONYEKWELU
JANUARY, 2025.
Introduction
• Imagine a world where finding your dream job is as easy as browsing
a curated online store. This presentation explores the design and
development of a career recommender system, a revolutionary
platform that leverages cutting-edge technology to connect job
seekers with ideal career paths. By analyzing individual skills,
interests, and aspirations, the system provides personalized
recommendations, empowering individuals to make informed
decisions about their future.
Motivation
• This project is motivated by the desire to empower individuals to
make informed career decisions. Navigating the evolving job market
can be a daunting challenge, often leaving individuals feeling
overwhelmed and uncertain about their future. By leveraging
technology, we aim to create a user-friendly system that simplifies the
career exploration process and helps individuals discover their
passions and potential.
Objectives
This project aims to:
• Develop a user-friendly interface that is intuitive and accessible for all
users to interact with the system.
• Implement a robust recommendation engine that utilizes machine
learning algorithms to analyze user data and generate personalized
career recommendations.
• Integrate comprehensive career information by incorporating data
from various sources, such as job boards, industry reports, and
educational institutions.
 LITERATURE REVIEW
Author Title objectives Contributions Limitation
Nguyen, T. T. Hybrid Approach to To investigate the Demonstrates the potential May require significant
Career Path effectiveness of combining of hybrid approaches that data preprocessing and
Recommendation traditional career integrate human expertise feature engineering, which
System Using Machine counseling methods with with AI for improved could be resource-
Learning. machine learning accuracy and user intensive. Limited
algorithms for satisfaction in career scalability for large-scale
personalized career guidance. applications with diverse
recommendations. user populations.

Chen, C., & A Personalized Career To explore the potential of Demonstrates the potential Requires significant
Liu, W. (2020) Recommendation deep learning models for of deep learning for computational resources
System Based on Deep personalized career providing highly accurate for training and inference,
Learning recommendations and and personalized career which may be a barrier for
compare their performance suggestions, surpassing some researchers and
with traditional rule-based the performance of institutions. Potential for
systems. traditional methods. bias in training data to
impact the fairness and
equity of
recommendations.
 LITERATURE REVIEW
Author Title Objectives Contributions Limitation
Nielsen, J., & Usability engineering. To establish a set of Provides a foundational May not fully address the
Norman, D. A. principles for designing framework for ensuring specific challenges of
(1994) user-friendly and effective that the career designing user interfaces
interactive systems. recommender system is for complex AI-powered
easy to use, efficient, and systems like career
enjoyable for users with recommenders.
varying levels of
technological proficiency.

Miller, K., & The Role of Artificial To provide a Identifies key challenges May not cover the most
Anderson, R. Intelligence in Career comprehensive overview and opportunities for AI recent advancements in
(2017) Counseling: A of AI applications in in the field of career AI and machine learning
Systematic Review. career counseling, guidance, informing the for career guidance, as it
including career development and was published in 2017.
assessment, job matching, implementation of AI-
and career exploration powered career guidance
tools. systems.
 LITERATURE
REVIEW
Author Title Objectives Contributions Limitation
Davies, J., & Ethical Considerations To highlight the ethical Provides a framework Ethical considerations
Evans, M. in the Development and implications of using AI for developing and are constantly evolving,
(2020) Deployment of AI- in career guidance, such deploying AI-powered and the framework may
Powered Career as data privacy, career guidance systems need to be updated to
Guidance Systems. algorithmic bias, and the responsibly, ensuring address emerging
potential for job fairness, transparency, challenges in AI ethics.
displacement. and user trust.

De Ruijt, M., Fairness and To investigate the Highlights the The focus on fairness
& Bhulai, S. Generalization in Job fairness and importance of fairness may not directly address
(2021) Recommender Systems generalization properties and ethical all aspects of user
of job recommender considerations in the experience and system
systems, focusing on design and development usability.
potential biases and of job recommendation
limitations. systems. Emphasizes the
need for algorithms that
are unbiased and
generalize well across
diverse user populations.
 Research Methodology
1. Data Collection:
• User Surveys/Assessments: Gather data on user interests, skills, values, and career aspirations
through comprehensive online surveys or assessments.
• Skill Assessments: Implement standardized tests or utilize existing skill assessment platforms to
assess user skills (e.g., cognitive abilities, technical skills).
• Personality Assessments: Incorporate personality assessments (e.g., Big Five personality traits) to
understand individual work preferences and potential career fit.
2. Data Processing and Analysis:
• Data Cleaning and Preprocessing: Clean and preprocess collected data to ensure data quality and
consistency.
• Feature Engineering: Extract relevant features from user data, such as skills, interests, personality
traits, and educational background.
• Machine Learning Algorithms: Utilize machine learning algorithms (e.g., decision trees, support
vector machines, collaborative filtering) to analyze user data and generate personalized career
recommendations.
 Research Methodology
• 3. System Development:
• User Interface (UI) Design: Develop a user-friendly and intuitive interface for easy interaction and
data input.
• System Architecture: Design and implement a robust system architecture to handle data storage,
processing, and delivery of recommendations.
• Integration with External Data Sources: Integrate with external data sources, such as job boards,
industry reports, and educational institutions, to provide comprehensive and up-to-date career
information.
• 4. System Evaluation:
• User Testing: Conduct user testing to evaluate the system's usability, effectiveness, and user
satisfaction.
• Performance Metrics: Evaluate the system's performance using metrics such as accuracy,
precision, recall, and user engagement.
• Iterative Refinement: Continuously monitor user feedback and system performance to identify
areas for improvement and refine the recommendation algorithm.
Expected Contribution to Knowledge
This project aims to contribute significantly to the field of career
guidance by: developing and evaluating a novel AI-powered career
recommender system; advancing our understanding of user behavior
and decision-making within the context of career exploration; refining
methodologies for data collection, analysis, and the utilization of AI
algorithms for personalized career recommendations; creating a user-
friendly tool that empowers individuals with informed career choices;
and addressing the limitations of existing approaches and exploring the
ethical considerations of AI in career guidance.
 References
• Nguyen, T. T., Nguyen, T. T., & Nguyen, T. T. (2021). A Hybrid Approach to Career Path
Recommendation System Using Machine Learning. International Journal of Advanced
Computer Science and Applications, 12(10), 442-450.
• Chen, C., & Liu, W. (2020). A Personalized Career Recommendation System Based on
Deep Learning. IEEE Access, 8, 107278-107292.
• Nielsen, J., & Norman, D. A. (1994). Usability engineering. Academic Press.
• Miller, K., & Anderson, R. (2017). The Role of Artificial Intelligence in Career Counseling: A
Systematic Review. Journal of Counseling & Development, 95(2), 137-148.
• Davies, J., & Evans, M. (2020). Ethical Considerations in the Development and
Deployment of AI-Powered Career Guidance Systems. AI & Society, 5(1), 127-142.
• User Experience Design for Career Guidance Systems: A Review (Smith, J., & Jones, A.,
2018). International Journal of Human-Computer Studies, 117, 1-11.
• Ethical Considerations in the Development and Deployment of AI-Powered Career
Guidance Systems (Davies, J., & Evans, M., 2020). AI & Society, 5(1), 127-142.