Web Based Selector – Applicant Simulation S...

Web Based Selector – Applicant Simulation System

Author Name : Janardhana Rao Alapati, Jyostna Karanam, Madhumitha Kandanoolu, Mahidhar Agraharapu, Abhinay Babu Chavali

ABSTRACT In today’s competitive job market, organizations face challenges in efficiently identifying and recruiting top talent while ensurng fairness, accuracy, and transparency in the hiring process. Traditional recruitment methods, including manual resume screening and subjective interviews, are often time-consuming, prone to bias, and inefficient in assessing candidate-job fit. This research presents an Integrated AI-Powered Talent Assessment System that leverages machine learning (ML), deep learning (DL), natural language processing (NLP), and explainable AI (XAI) to automate and optimize resume analysis, AIdriven interviewing, and predictive hiring analytics. The proposed system employs BERT- based NLP models to extract and rank candidate resumes based on job descriptions, reducing screening time by 78%. An AI-driven interview module integrates speech-to-text conversion, sentiment analysis, and facial expression recognition to evaluate communication skills, emotional intelligence, and technical expertise, improving candidate assessment by 43%. Furthermore, predictive analytics models (XGBoost, Random Forest, and Artificial Neural Networks) forecast candidate success and retention probability with an AUCROC score of 89.2%, enabling data driven, unbiased hiring decisions. The inclusion of explainable AI techniques (SHAP, LIME) ensures transparency and fairness, mitigating bias in recruitment by 31%.The results indicate that this AI-powered hiring framework significantly enhances recruitment efficiency, reducing hiring costs by 54%, decreasing time-to-hire by 68%, and improving candidate-job fit by 47%. Future enhancements will focus on industry-specific assessments, psychometric evaluations, blockchain-based credential verification, and federated learning for improved security, scalability, and ethical AI adoption. This research demonstrates the transformative potential of AI-driven talent assessment systems, paving the way for a more intelligent, scalable, and unbiased recruitment ecosystem.