OPTIMIZING TALENT ACQUISITION: A DATA-DRIVEN APPROACH USING LOGISTIC REGRESSION IN HUMAN RESOURCE MANAGEMENT
DOI: https://doi.org/10.xxxxxx

JOURNAL OF RESEARCH PERSPECTIVES IN MULTIDISCIPLINARY SCIENCE, EDUCATION AND TECHNOLOGY (RPSET) 
Volume 1 Issue 1, Jan – March 2026

Abstract
This paper investigates the application of logistic regression algorithms to enhance recruitment efficiency in Human Resource Management. In an era of data-driven decision-making, traditional recruitment methods often prove inefficient, subjective, and costly. This study presents a comprehensive framework for implementing logistic regression to predict candidate suitability, thereby streamlining the talent acquisition process. We examine how historical hiring data, including candidate qualifications, assessment scores, and interview performance, can be leveraged to build predictive models that identify high-potential candidates with greater accuracy. The methodology outlines data preprocessing, feature selection, model training, and validation specific to recruitment contexts. Comparative analysis with traditional screening methods demonstrates significant improvements in key metrics: reducing time-to-hire by approximately 35%, decreasing cost-per-hire by 28%, and improving first-year retention rates by 22%. The discussion addresses implementation challenges, ethical considerations regarding algorithmic bias, and practical integration strategies for HR systems. This research provides both theoretical insights and practical guidelines for organizations seeking to transform their recruitment processes through predictive analytics.

Authors: Mr. A. Sheik Mohammed and Dr. M. Kotteshwari

Keywords: Predictive Recruitment, Logistic Regression, HR Analytics, Talent Acquisition, Data-Driven Hiring, Candidate Selection