Authors : Anusha Rokkam; Pasupuleti Lakshmi Komali; Bhavana Pamidakula; G.Archana

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/ykykf4hp

Scribd : https://tinyurl.com/yndpcwvn

DOI : https://doi.org/10.38124/ijisrt/26apr1615

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : In today’s dynamic job market, students face challenges in selecting career paths that best fit their academic backgrounds and skill sets. This project presents a personalized career recommendation system that leverages machine learning and data science techniques to provide precise career guidance. The system processes a comprehensive dataset that includes academic records, technical and soft skills, and personal preferences of students. Through exploratory data analysis and feature engineering, the system identifies significant correlations between different skills and career options. Multiple supervised machine learning algorithms, including Logistic Regression, Random Forest, and Support Vector Machines, are trained and evaluated using metrics such as accuracy, precision, recall, and F1-score to ensure reliable recommendations. Moreover, K-Means clustering groups similar student profiles to enhance the accuracy of suggestions via collaborative filtering. A user-friendly web application built using Flask allows students to input their profiles and receive personalized career recommendations alongside feature importance visualizations and actionable skill gap analyses. The system achieves high predictive performance, offering a practical, scalable solution for educational institutions and career counselors to assist students in making informed career decisions, showcasing the applied potential of AI and data science.

Keywords : Career Recommendation, Machine Learning, Data Science, Feature Engineering, Student Profiling, Flask Deployment, Model Evaluation, Collaborative Filtering.

References :

1. F. Parsons, Choosing a Vocation. Boston, MA, USA: Houghton Mifflin, 1909. (Foundational Trait-Factor Theory).
2. J. L. Holland, Making Vocational Choices: A Theory of Vocational Personalities and Work Environments. Odessa, FL, USA:
3. Psychological Assessment Resources, 1997.
4. J. Zhang, "Research on the advanced career guidance system of big data under the situation of current students," Journal of Physics: Conference Series, vol. 1744, no. 4, p. 042111, 2021. doi: 10.1088/1742-6596/1744/4/042111.
5. L. Breiman, "Random Forests," Machine Learning, vol. 45, no. 1, pp. 5-32, 2001. (Primary Reference for the Random Forest Algorithm).
6. V. Vapnik, The Nature of Statistical Learning Theory. New York, NY, USA: Springer-Verlag, 1995. (Primary Reference for Support Vector Machines).
7. C. Madhan Mohan, "Career Prediction System for Computer Science and Engineering Students using Machine Learning," International Journal of Computer Applications, vol. 182, no. 45, pp. 24-29, 2019.
8. S. Rane, A. Kulkarni, and M. Shah, "Career recommendation system using machine learning," in Proc. Int. Conf. on Inventive Systems and Control (ICISC), 2019, pp. 112-116.
9. T. K. Guntupalli et al., "Enhanced Career Recommendation System using Ensemble Learning and Feature Engineering," IEEE Access, vol. 12, pp. 4501245025, 2024. (Reference for the Hybrid Predictive Era).
10. J. MacQueen, "Some methods for classification and analysis of multivariate observations," in Proc. 5th Berkeley Symp. Math. Statist. and Prob., vol. 1, 1967, pp. 281-297. (Primary Reference for K-Means Clustering).
11. M. Sahid and A. Pratama, "Aptitude and Interest-Based Career Prediction using Naive Bayes and Decision Trees," Journal of Computing and Educational Technology, vol. 5, no. 2, pp. 88-95, 2022.
12. Grinberg, M., Flask Web Development: Developing Web Applications with Python. Sebastopol, CA, USA: O'Reilly Media, 2018. (Reference for the Implementation Environment).
13. Pedregosa, F., et al., "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, vol. 12, pp. 28252830, 2011.