Optimizing Human Resource Allocation Through AI-Driven Resume Classification and Grading

This paper presents a comprehensive AI-driven framework for optimizing human resource allocation through automated resume screening, classification, and Grading. Utilizing advanced natural Ianguage processing (NLP) techniques and large language models (LLMs) such as GPT-۳.۵, the proposed method aims to enhance the efficiency and objectivity of the recruitment process. We generated a diverse dataset of Perisian resumes and employed generative models to preprocess and categorize the resumes into various job-specific categories. Our experimental results demonstrate significant improvements in classification accuracy, grading, and summarization metrices compared to baseline models. Additionally, the automated framework is shown to be approximately ۱۰ times faster than traditional manual screening methods, highilghting its potential for widespread adoption in modern HR practices. Future work will focus on further refining the model and expanding its applicability to other languages and job markets.

کلیدواژه ها:

Hurman Resource Allocation ، Resume Screening ، Natural Language Processing ، Large Language Models ، GPT-۳.۵ ، AI in Recruitment