AI-Driven Resume Classification and Job Recommendation System

This paper presents an Artificial Intelligence (AI)-
driven resume screening and job recommendation system de-
signed to improve the job-matching process by leveraging ma-
chine learning (ML) and Natural Language Processing (NLP)
techniques. The system uses various models to predict job
suitability accurately and efficiently, enhancing the recruitment
experience for both job seekers and employers. In our work, we
have employed various machine learning models: Latent Dirichlet
Allocation (LDA), K Nearest Neighbors (KNN), Long Short-Term
Memory (LSTM), Gated Recurrent Units (GRU), transformer
and Gradient Boosting (GB) to classify the right categories of
resume. Furthermore, a content-based filtering approach and
KNN algorithm have been used to recommend top n jobs to users
by analyzing and measuring the similarity of user resumes and
explicit job listing features. Our experimental results revealed
that, among different models gradient boosting achieved the
highest accuracy of 99.65% in classifying resumes into correct
categories, indicating its superior performance in capturing long-
range dependencies in the text data. This study aims to bridge
the gap between job seekers and employers, providing a robust
and scalable solution for the job market.