Advanced Recruitment Strategies in Business Intelligence Systems: A Comparative Study of Machine Learning Models

This project features Streamlit-based software that uses business insights to improve the hiring process. Users can upload resumes in various formats (PDF, DOCX and plain text), and the application will extract and pre-process the material before comparing and analyzing it using machine learning models. By using spaCy's natural language processing framework, the system picks up redundancies in resumes to bring out the important details. This application mainly uses the three techniques, i.e. Random forest, logistic regression, and K-nearest neighbors. Every model goes through a method that converts textual data to a machine learning-ready format with TF-IDF vectorization. These models are then used to classify resumes based on the categories of existing data sets. Each model is evaluated for correctness, and the final is presented as category distributions, confusion matrices, and bar graphs. This proposed approach excels at cockpit data visualizations with the merge of various models of machine learning making it plausible for a broader picture in the scenery of resume matching. The error- free, user-friendly visual feedback and intuitive user interface of the proposed system would set a reliable pre-screening tool for the recruiters. The proposed system represents a new and innovative approach to contractually integrating text preprocessing, visual analysis, and model diversity in the context of these problems.