Job Matcher Project

Ong, Weng Kai (2025) Job Matcher Project. Final Year Project (Bachelor), Tunku Abdul Rahman University of Management and Technology.

Text RDS_Ong Weng Kai_FullText.pdf Restricted to Registered users only Download (1MB)

Abstract

The project aims to revolutionize the job recruitment process by introducing an AI-driven system that enhances how job seekers are matched with suitable opportunities. It addresses key recruitment challenges such as managing high application volumes and unclear job descriptions, which often lead to inefficiencies and increased hiring costs. By leveraging natural language processing techniques like cosine similarity and TF-IDF vectorization, the system accurately aligns resumes with job listings, streamlining the screening process and minimizing mismatches. The scope of this project encompasses developing a comprehensive platform that includes features for resume uploading, preprocessing, and an employer interface for robust job management. Both job seekers and employers benefit from functionalities such as advanced filtering, job ranking by relevance, and secure logins for managing postings and applicant data. Methodologically, the system is built using Python with Streamlit for the interface and MongoDB for backend data storage, supporting structured storage and retrieval of job and user data. The architecture is designed to process data in real-time, ensuring that job listings and applicant matches are consistently updated. Comprehensive testing covered various aspects including functionality, usability, and security. Results affirmed the system's effectiveness in simplifying recruitment processes, offering timely and precise job matches. Nevertheless, the system's current version does not integrate with external job boards and could be improved by incorporating real-time data feeds for a more extensive listing of opportunities. In conclusion, the project underscores the potential of AI in recruitment, significantly reducing hiring timelines and costs. Future enhancements could focus on expanding system integration, increasing scalability, and implementing adaptive AI models to better meet changing market demands.