AI-Based Resume Screening and Career Path Recommendation System

Abstract

Many companies\' recruitment procedures entail the manual evaluation of several resumes, which is laborious and prone to human bias. In order to overcome this difficulty, this project suggests an AI-based Resume Screening and Career Path Recommendation System that evaluates candidates automatically and makes recommendations for appropriate career pathways based on each person\'s talents and qualifications. The system makes advantage of contemporary web technologies, such as Tailwind CSS for effective and responsive user interface design and Next.js for frontend development. Resumes are processed using a Python backend program that extracts pertinent data, including education, experience, and abilities. A machine learning model called Logistic Regression is used to analyse the gathered data and forecast the suitability of candidates for particular positions. The suggested approach seeks to shorten the hiring process, increase the accuracy of screening, and help applicants choose the right career path. The platform improves applicant career planning and recruiter productivity by utilising data-driven approaches and artificial intelligence. The system is a useful tool for contemporary recruiting and talent management systems since experimental evaluation shows that it can efficiently classify resumes and produce insightful career recommendations. By comparing candidate skill profiles with industry role requirements, the system not only screens resumes but also suggests possible career routes. This gives consumers information about employment options that fit their skills and interests. Supabase is the database solution that allows for effective data management while safely storing user data, resumes, and model outputs. Scalability, quick processing, and better decision-making are guaranteed in recruitment workflows when machine learning is integrated with a contemporary full-stack architecture.

Introduction

This paper presents an AI-based Resume Screening and Career Path Suggestion System designed to automate the recruitment process and provide personalized career recommendations. Traditional resume screening is time-consuming, prone to human bias, and inefficient when handling large volumes of applications. The proposed system addresses these challenges by using machine learning and modern web technologies to analyze resumes, evaluate candidate profiles, calculate Applicant Tracking System (ATS) compatibility scores, and recommend suitable job roles.

The system is built on a three-tier architecture consisting of a Next.js and Tailwind CSS frontend, a Python/FastAPI backend, and a Supabase cloud database. Users upload resumes in PDF format through a web interface. The backend extracts important information such as skills, education, work experience, and word count using text processing techniques. A Logistic Regression machine learning model then classifies the candidate profile and predicts the most suitable career paths based on extracted skills. The system also calculates an ATS score using resume content quality and detected skills and provides actionable suggestions to improve resume quality.

The literature survey highlights the growing adoption of AI and machine learning in recruitment, discussing techniques such as Logistic Regression, Decision Trees, and Support Vector Machines for resume classification. It also emphasizes the integration of cloud databases and web-based platforms to create scalable, user-friendly recruitment systems.

The methodology includes resume upload, text extraction, skill identification, ATS evaluation, career prediction, and visualization of results. The system displays extracted skills, ATS compatibility scores, the top three recommended career paths, and confidence scores using interactive charts, helping users understand how well their resumes align with various job opportunities.

Experimental evaluation demonstrated that the system efficiently processed PDF resumes, accurately extracted candidate information, calculated ATS scores, and generated meaningful career recommendations. The intuitive web interface allowed users to upload resumes easily and receive instant feedback. However, the system’s accuracy depends on the quality and completeness of resume content, currently supports only a limited number of job roles, and was evaluated using a relatively small dataset. Overall, the proposed solution offers a scalable, intelligent, and user-friendly platform that improves recruitment efficiency while helping job seekers identify suitable career paths and enhance their resumes.

Conclusion

The suggested platform combines a Supabase database, a Python backend, and a Next.js frontend to produce a scalable and intuitive web application. Important details like abilities and content length are extracted from uploaded resumes by the system using PDF parsing algorithms. Word count and identified abilities are used to produce an ATS compatibility score that gives consumers a sense of how effective their resumes are. The best career pathways from predetermined professions, such as data scientist, software developer, and web developer, are predicted using the logistic regression model. The outcomes are presented via an easy-to-use interface that uses Chart.js to visualize confidence, identify skills, and suggest careers. The system can effectively analyze candidate profiles and produce insightful results, according to experimental testing using example resumes. All things considered, the suggested solution offers job seekers a useful tool that helps with resume evaluation and career counseling

References

[1] H. I. Borude, “AI-based Resume Screening System for Automated Hiring,” International Journal of Computing, Programming and Database Management (IJCPDM), vol. 6, no. 2, pp. 133–136, Jun. 2025. [2] A. Sable, A. Macharekar, S. Wagh, P. Udbatte, and J. Nanajkar, “AI Powered Application Tracking System: With NLP Based Resume Scoring,” International Journal of Creative Research Thoughts (IJCRT), vol. 13, no. 6, pp. c594–c598, Jun. 2025. [3] S. Ramchandani, R. Sharma, and P. Mehta, “AI Resume Analyzer: NLP-Driven Recruitment System,” International Journal of Science, Engineering and Technology (IJSET), vol. 13, no. 5, pp. 112–118, May 2025. [4] Lingaya’s Vidyapeeth, “Advanced AI Based Resume Screening,” Conference on Emerging Computing Technologies (CECT), pp. 45–52, Apr. 2025. [5] Lo, Y. Zhang, and K. Lee, “AI Hiring with LLMs: A Context-Aware and Explainable Multi-Agent Framework for Resume Screening,” IEEE/CVPR Workshop Proceedings, pp. 210–219, Jun. 2025. [6] V. Lokam, R. Reddy, and S. Rao, “AI-Based Career Guidance System,” International Journal of Creative Research Thoughts (IJCRT), vol. 11, no. 2, pp. 88–95, Feb. 2025. [7] M. Brindha, K. Kumar, and R. Singh, “AI-Powered Resume Optimizer and Job Recommendation System,” Journal of Emerging Technologies and Innovative Research (JETIR), vol. 12, no. 3, pp. 301–308, Mar. 2025 [8] V. R. S. B. Yalamarthi, “Artificial Intelligence in Recruitment: Transforming Talent Acquisition Practices,” International Journal of Innovations & Research Analysis (IJIRA), vol. 5, no. 3, pp. 01–11, Mar. 2025. [9] g P. Pawar, S. Deshmukh, and A. Kulkarni, “AI-Powered Recruitment System,” International Journal of Creative Research Thoughts (IJCRT), vol. 11, no. 4, pp. 210–216, Apr. 2025. [10] S. V. Gouda and B. R., “A Machine Learning-Based Career Recommender System,” National Institute of Engineering Technical Reports, pp. 55–62, May 2025. [11] R. Agarwal and S. Gupta, “AI-Driven Resume Screening Using Deep Learning,” International Journal of Computer Applications (IJCA), vol. 182, no. 12, pp. 45–52, Sep. 2025. [12] K. Patel and J. Shah, “Career Path Recommendation Using Machine Learning,” International Journal of Advanced Computer Science and Applications (IJACSA), vol. 16, no. 10, pp. 77–84, Oct. 2025.

Copyright

Copyright © 2026 Lanka Satya Surya Sai Vijay Kumar Sarma, Gella Uday Kumar, Achanta Gopi , Tadi Satya Manasa , Kasi Anvesh, Onteddu Siva Rama Krishna. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.