PerfectHR: Using AI to Reduce Candidate-Job Mismatch and Improve Recruitment Efficiency

Abstract

The recruitment process is critical for organizations to find the right talent. However, existing recruitment software often faces issues like candidate-job mismatches and biases, leading to inefficient hiring processes. This paper presents PerfectHR, a recruitment software solution designed to reduce candidate-job mismatches and improve recruitment efficiency using artificial intelligence. The software integrates a logistic regression model for candidate classification and OpenAI’s GPT-4 language model for CV summarization. PerfectHR addresses bias in the dataset and algorithm by excluding sensitive features such as age and gender to ensure that they do not influence the model predictions. The application was developed using React.js for the frontend, Node.js for the backend, MongoDB for database management, and deployed on Vercel. Initial testing indicates that PerfectHR provides a reliable and user-friendly experience, effectively supporting job postings, candidate evaluations, and communication. Future work will focus on expanding the training dataset to cover a broader range of job types and further refining the application to improve performance and scalability.