The Research Department of Economics and Management of Tadbir Nikan Business, Marketing, and Finance Open 3092-6238 3 Serial Number 14 2026 03 01 Application of Machine Learning in Predicting Performance and Optimizing the Recruitment Process Application of Machine Learning in Predicting Performance and Optimizing the Recruitment Process 1 9 10.61838/bmfopen.308 EN Journal Article 2025 06 12 <p>The main objective of this study is to examine the role and effectiveness of Machine Learning (ML) algorithms in predicting employee performance and optimizing the recruitment process. This article seeks to demonstrate how data-driven models can be used to reduce human errors, enhance decision-making accuracy, and improve organizational justice. This research is applied in nature and has been conducted using a descriptive–analytical approach. The data consisted of résumé information, psychometric test results, educational records, and employee performance indicators, which were preprocessed and subjected to feature selection before being fed into ML algorithms. Four algorithms—Decision Tree, Random Forest, Support Vector Machine (SVM), and Artificial Neural Network (ANN)—were employed, and their performance was evaluated using metrics such as accuracy, F1 score, and Area Under the Curve (AUC). The results showed that the Random Forest algorithm and ensemble models achieved the highest accuracy in predicting job performance. Furthermore, data analysis revealed that personality traits such as conscientiousness and extraversion, along with work experience and cultural fit, were the strongest predictors of job success. The findings indicated that ML can significantly reduce errors caused by human bias and make decision-making more data-driven. Machine learning has created unprecedented opportunities for transforming Human Resource Management (HRM). By enhancing prediction accuracy, reducing costs resulting from unsuccessful hires, and improving organizational justice, this technology can transform recruitment from an intuitive activity into a scientific, evidence-based decision-making process.</p> https://bmfopen.com/index.php/bmfopen/article/download/308/241