Scholarlink

Employee promotion is a critical practice of human resource management, reflecting both recognition and strategic workforce development. This study evaluates the performance of five machine learning (ML) models, Logistic Regression, Random Forest, Decision Tree, XGBoost, and Support Vector Machines (SVM), and a deep learning (DL) model, Artificial Neural Networks (ANN), in predicting promotions. Using a dataset of 54,808 records, the models were trained and tested on balanced data with SMOTE applied to address class imbalance. Among the models, XGBoost outperformed others, achieving the highest accuracy (93.76%) and precision (86.34%). Random Forest and ANN also showed competitive results, highlighting their potential in HR analytics. The ultimate goal is to accurately predict employee promotions, enabling organizations to optimize their workforce strategies, enhance employee satisfaction, and foster career development among deserving individuals.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Promotion Prediction Through AI: Evaluating Machine Learning and Deep Learning Models

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Adil Benabou,
  • Fatima Touhami,
  • Driss Ait-Bourigue

摘要

Employee promotion is a critical practice of human resource management, reflecting both recognition and strategic workforce development. This study evaluates the performance of five machine learning (ML) models, Logistic Regression, Random Forest, Decision Tree, XGBoost, and Support Vector Machines (SVM), and a deep learning (DL) model, Artificial Neural Networks (ANN), in predicting promotions. Using a dataset of 54,808 records, the models were trained and tested on balanced data with SMOTE applied to address class imbalance. Among the models, XGBoost outperformed others, achieving the highest accuracy (93.76%) and precision (86.34%). Random Forest and ANN also showed competitive results, highlighting their potential in HR analytics. The ultimate goal is to accurately predict employee promotions, enabling organizations to optimize their workforce strategies, enhance employee satisfaction, and foster career development among deserving individuals.