AI Job Matching with Gradient Boosting Machine

Chuah, Wai Lam (2026) AI Job Matching with Gradient Boosting Machine. Final Year Project (Bachelor), Tunku Abdul Rahman University of Management and Technology.

Text RIT_Chuah Wai Lam_FullText.pdf Restricted to Registered users only Download (5MB)

Abstract

This project presents an AI-powered job matching platform that addresses inefficiencies in traditional recruitment processes by leveraging Gradient Boosting Machines (GBM). In today's competitive job market, both job seekers and employers face significant challenges in finding suitable matches due to outdated resume-based screening methods and manual processes. The platform utilizes ASP.NET MVC and ML.NET to create personalized job recommendations based on user profiles, skills, and preferences. The system implements several key functionalities including AI-driven job matching, advanced search filtering, and sentiment analysis of company reviews. Using the Waterfall methodology, the project progresses through systematic phases from requirements analysis to implementation and testing. The GBM algorithm serves as the core matching engine, analyzing multiple parameters to determine optimal job-candidate fits, while sentiment analysis classifies the company reviews. Preliminary testing indicates improved matching accuracy and reduced screening time compared to traditional methods. The platform contributes to addressing unemployment challenges by providing more efficient, personalized recruitment experiences for both employers and job seekers, ultimately aiming to create more successful and satisfying job placements in an increasingly complex employment landscape.