Resume application tracking system using AI | IJCSE Volume 9 – Issue 6 | IJCSE-V9I6P14

The manual process of screening résumés for job applications is a significant bottleneck in modern recruitment, characterized by being time-consuming, labour-intensive, and susceptible to human bias. This paper presents the architecture of an intelligent Applicant Tracking System (ATS) that leverages Artificial Intelligence, specifically Natural Language Processing (NLP), to automate and enhance the résumé screening process. The proposed system first parses unstructured résumés in various formats to extract key information such as contact details, skills, and work experience using Named Entity Recognition (NER). Subsequently, it employs a deep learning-based semantic analysis model, utilizing pre-trained transformer embeddings (e.g., BERT), to understand the contextual meaning of both the résumé and the job description. A relevance score is then calculated for each candidate using cosine similarity, allowing for an objective and context-aware ranking. This AI-driven approach significantly increases the efficiency of shortlisting candidates, aims to reduce unconscious bias, and provides recruiters with a powerful tool to identify the most suitable applicants from a large pool.

This paper has outlined the architecture of an intelligent, AI-based Applicant Tracking System. By combining modern NLP techniques for information extraction with deep learning-based semantic analysis, the system provides a fast, accurate, and more objective way to screen and rank job applicants. It addresses many of the core deficiencies of manual screening and older ATS technologies, offering a powerful tool to streamline the modern recruitment process. The model has accuracy of 90% Future work will focus on extending the system’s intelligence and capabilities: 1.Skill Gap Analysis: Automatically identifying the key skills a promising candidate is lacking for a specific role. 2.Automated Interview Scheduling and Pre-screening: Integrating a chatbot to ask basic screening questions and schedule interviews with qualified candidates. 3.Predictive Performance Analytics: Training a model on historical hiring data to predict the future job performance of candidates based on their résumé characteristics. 4.Advanced Bias Detection and Mitigation: Implementing sophisticated fairness toolkits to continuously audit the model’s predictions across different demographic groups and apply debiasing techniques.

[1]Title: A Review of Keyword-Based and Semantic Search for Applicant Tracking Systems. Author(s): M. F. O. and A. A. E. Link:https://ieeexplore.ieee.org/document/ 10394101 [2]Title: Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. Author(s): J. Lafferty, A. McCallum, and F. Pereira. Link:. https://ieeexplore.ieee.org/document/1039 4101 [3]Title: Efficient Estimation of Word Representations in Vector Space. Author(s): T. Mikolov, K. Chen, G. Corrado, and J. Dean. Link: https://arxiv.org/abs/1301.3781 [4]Title: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Author(s): J. Devlin, M. W. Chang, K. Lee, and K. Toutanova. Link: https://arxiv.org/abs/1810.04805 [5]Title: A BERT-based Approach for Job- Résumé Matching. Author(s): Y. Zhang and C. S. Lin. Link: Not provided in the reference. [6]Title: A Survey on Automated Résumé Screening. Author(s): P. F. F. de Souza, J. C. D. Lopes, and D. G. F. de Souza. Link: https://doi.org/10.1109/SMC53992.2023.1 0394101 [7]Title: Resume and Job Description Matching Using BERT. Author(s): S. Singh, M. Pathak, and H. Kumar. Link: https://doi.org/10.1109/ICCCA55294.2022 .9972016 [8]Title: Information Extraction from Resumes using Named Entity Recognition with Deep Learning. Author(s): N. B. Kulkarni and A. R. C. Prasad. Link: https://doi.org/10.1109/ICAC353642.2021 .9697220 [9]Title: Intelligent Recruitment Management System. Author(s): S. Goel, A. Sharma, and A. Singh. Link: https://doi.org/10.1109/ICICCS48265.202 0.9120977 [10]Title: ATS: A Smart AI Recruitment System Using NLP. Author(s): P. S. Priyadarshini, M. S. Kumar, M. J. R. Kumar and G. T. Kumar. Link: https://doi.org/10.1109/ICAECA55558.20 22.10022442 [11]Title: AI and Algorithmic Bias in Recruitment: A Review. Author(s): S. Raghavan, A. P. Duggirala and P. M. Kumar. Link:https://doi.org/10.1109/ICACRS5551 7.2022.10029141