Volume 14, Issue 11

Career Compass AI

Author

Abhijit Bajrang Rahikar, Mayur Madhukar Patil, Ganesh Vishnu Wamane, Dinesh Kishor Patil, Prof. Khemnar K. C.

Abstract

Abstract
In today’s competitive job market, evaluating the compatibility between a candidate’s resume and a job description remains a critical yet time-consuming task for recruiters and career counsellors. This paper presents Career Compass AI  an intelligent system designed to automate and enhance the resume–job matching process using Natural Language Processing (NLP) and ChatGPT-based semantic analysis. The system extracts key features such as skills, educational qualifications, experience, and keywords from both resumes and job descriptions, and compares them to compute a compatibility score. The approach eliminates the need for manual candidate screening by leveraging NLP-based keyword extraction and semantic similarity matching techniques. The results are presented on a dynamic web-based dashboard that displays the compatibility score, matched and missing skills, educational relevance, and AI-generated improvement suggestions. A prototype implementation demonstrates the system’s ability to assess resume job fit effectively, achieving an average compatibility score of 82% for candidates whose profiles closely align with the given job requirements. The proposed system simplifies the recruitment process, aids students in understanding skill gaps, and serves as a foundation for future AI-driven career guidance and recruitment tools. 

References:
[1]    S. Patel and M. Sharma, “Career prediction using Natural Language Processing and Machine Learning techniques,” International Journal of Computer Applications, vol. 183, no. 25, pp. 12–17, 2022.
[2]     P. Kumar and A. Reddy, “AI-driven career guidance using semantic similarity measures,” IEEE Access, vol. 11, pp. 106453–106465, 2023.
[3]     R. Singh, S. Mehta, and N. Gupta, “Deep learning-based career recommendation using student profile analysis,” Procedia Computer Science, vol. 218, pp. 554–562, 2023.
[4]     V. Mehta and A. Gupta, “Context-aware job–resume similarity using BERT-based embeddings,” Journal of Intelligent & Fuzzy Systems, vol. 45, no. 2, pp. 1901–1912, 2023.
[5]    M. Tanwar, S. Kaur, and R. Arora, “Leveraging ChatGPT for automated resume summarization and skill extraction,” International Journal of Artificial Intelligence Research, vol. 49, no. 1, pp. 88–97, 2024.
[6]     D. Roy and A. Sinha, “Generative AI for intelligent recruitment: A semantic analysis approach,” Expert Systems with Applications, vol. 237, Article ID 121754, 2024.
[7]     H. Gupta and S. Bansal, “A hybrid NLP-based recommendation system for job–candidate matching,” Procedia Computer Science, vol. 199, pp. 231–239, 2022.
[8]    L. Chen, Y. Wu, and P. Zhang, “Skill-based job recommendation using natural language processing and contextual embeddings,” Knowledge-Based Systems, vol. 273, Article ID 110628, 2023.
[9]    E. Loper and S. Bird, “NLTK: The Natural Language Toolkit,” Proceedings of the ACL Workshop on Effective Tools and Methodologies for Teaching Natural Language Processing and Computational Linguistics, Philadelphia, pp. 63–70, 2002.
[10]     M. Honnibal, I. Montani, S. Van Landeghem, and A. Boyd, “spaCy: Industrial-strength Natural Language Processing in Python,” Zenodo, DOI: 10.5281/zenodo.1212303, 2020.
[11]     OpenAI, “GPT-3.5 and GPT-4 API documentation,” OpenAI Developer Platform, [Online]. Available: https://platform.openai.com/docs, Accessed: 2025.
[12]     M. Arora and K. Deshmukh, “Large Language Models for contextual text similarity and semantic reasoning,” Journal of Artificial Intelligence and Data Science, vol. 7, no. 3, pp. 155–167, 2024.
 

DOI

PAGES : 1663-1667 | 2 VIEWS | 1 DOWNLOADS

Download Full Article