DOCUMENT-DRIVEN AI SOLUTIONS FOR TALENT OPTIMIZATION
Abstract
The recruitment process is a critical function in modern organizations, and manual screening of resumes is often time-consuming and error-prone. This paper proposes a structured and semi-automated framework for extracting key resume attributes using AI and ranking candidates through a configurable scoring model. By integrating natural language processing, automation tools, and visualization platforms, the system enhances decision-making efficiency for recruiters. The solution uses modular Python scripts and APIs to parse resumes, score candidates, and present the results through dashboards, with an optional feedback loop for further evaluation. In particular, the proposed system leverages the capabilities of GPT-3.5 through LangChain to semantically understand resume content, enabling more accurate parsing and ranking. The system architecture supports end-to-end automation, starting from resume intake via email, intelligent parsing, rule-based scoring, and finally, interactive result visualization.
Author(s) and co-author(s) jointly and severally represent and warrant that the Article is original with the author(s) and does not infringe any copyright or violate any other right of any third parties and that the Article has not been published elsewhere. Author(s) agree to the terms that the IJO Journal will have the full right to remove the published article on any misconduct found in the published article.
