This study explores the role of artificial intelligence (AI) in human resource management (HRM), with a focus on recruitment, employee retention, and performance optimization. Through a PRISMA-based systematic literature review, the paper examines many machine learning algorithms including XGBoost, SVM, random forest, and linear regression in decision-making related to employee-attrition prediction and talent management. The findings suggest that these technologies can automate HR processes, reduce bias, and personalize employee experiences. However, the implementation of AI in HRM also presents challenges, including data privacy concerns, algorithmic bias, and organizational resistance. To address these obstacles, the study highlights the importance of adopting ethical AI frameworks, ensuring transparency in decision-making, and developing effective integration strategies. Future research should focus on improving explainability, minimizing algorithmic bias, and promoting fairness in AI-driven HR practices.

In the context of employee attrition prediction using imbalanced tabular data, we propose a reproducible, leakage-aware evaluation protocol and validate it on the IBM HR Attrition dataset. We perform the train/test split prior to any rebalancing; SMOTE (Synthetic Minority Over-sampling Technique) is applied exclusively within the training portion of each fold in stratified 5-fold cross-validation, while the test set remains untouched. One-Hot Encoding is performed consistently using pd.get_dummies. We benchmark Logistic Regression, Random Forest, ExtraTrees, LightGBM, and XGBoost using imbalance-aware metrics: F1 for the minority class, PR-AUC reported as Average Precision (AP), and ROC-AUC reported both in cross-validation and on the held-out test set. XGBoost attains the best mean AP in cross-validation (0.556 ± 0.056). Logistic Regression achieves the highest mean F1 (0.439 ± 0.048), while LightGBM yields the best mean ROC-AUC (0.791 ± 0.026). On the test set, XGBoost achieves a precision value of 0.65 and a recall value of 0.45 at a fixed threshold of 0.5. Overall, the results highlight a trade-off between stable minority-class detection (Logistic Regression) and stronger risk ranking performance (boosting models) under class imbalance.