Integrating machine learning and explainable AI for employee attrition prediction in HR analytics
Maytha Al-Ali1, Majed Alwateer2, Shatha Abed Alsaedi2
1College of Business, Zayed University, Dubai, 19282, UAE.
Scientific Reports
|February 12, 2026
Summary
Predicting employee attrition is crucial for retention. This study introduces a machine learning framework using SHAP (SHapley Additive exPlanations) to identify key drivers like overtime and job satisfaction, enabling proactive talent management.
Area of Science:
- Human Resources Analytics
- Machine Learning in Business
- Predictive Modeling for Talent Management
Background:
- Employee attrition significantly impacts organizational productivity, morale, and financial health.
- Effective retention strategies require accurate prediction of attrition and understanding of its root causes.
- Current HR analytics often face challenges in predictive accuracy, interpretability, and generalizability.
Purpose of the Study:
- To propose and evaluate a comprehensive machine learning framework for predicting employee attrition and job change likelihood.
- To integrate advanced predictive models with explainability tools for transparent and fair HR analytics.
- To provide actionable insights for proactive talent management and mitigate employee turnover.
Main Methods:
- Utilized robust preprocessing pipelines and state-of-the-art machine learning models, including Adaptive Boosting (AB) and Histogram Gradient Boosting (HGB).
- Employed SHAP (SHapley Additive exPlanations) for global and local interpretability analysis to identify key attrition predictors.
- Addressed challenges such as class imbalance, feature selection, and model interpretability.
Main Results:
- Achieved near-optimal performance metrics (Precision, Recall, F1-score, Accuracy) across diverse datasets.
- Identified critical predictors of employee attrition, including OverTime, JobLevel, and JobSatisfaction, through SHAP visualizations.
- Demonstrated the framework's adaptability, scalability, and potential for real-time deployment in HR analytics.
Conclusions:
- The proposed machine learning framework offers a practical solution for mitigating employee turnover.
- Enhanced predictive accuracy and interpretability in HR analytics lead to more effective talent management strategies.
- The study advances HR analytics by bridging gaps in predicting and understanding employee attrition, safeguarding human capital investments.
Keywords:
Data balancing techniquesEmployee attrition predictionFeature selectionHyperparameter optimizationJob change analysisMachine learning in HR analyticsSHAP explainabilityMore Related Videos
Related Concept Videos
02:27Predicting Molecular Geometry
46.1K
VSEPR Theory for Determination of Electron Pair Geometries
46.1K
01:19Machines
581
Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. One example of a machine is the cutting plier, which is used to cut wires by applying forces to its handles. When equal and opposite forces are exerted on the handles of the cutting plier, they cause the cutting edges to come together and apply equal and opposite reaction forces on the wire, which are greater than the applied forces.
A free-body diagram of the...
A free-body diagram of the...
581
01:21Development of Analytical Methods
2.4K
An analytical methodology can be divided into four sequential steps: technique, method, procedure, and protocol. A technique is a scientific principle that rationalizes a specific phenomenon through chemical measurements. Adapting a technique for analyzing a sample of interest is termed a method. The procedure outlines the directions for performing the analysis via an analytical method. The protocol is the detailed guidelines on the procedure, which should be strictly followed to obtain the...
2.4K
01:30Machines: Problem Solving II
678
Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. Consider a lifting tong carrying a 100 kg load. It comprises movable sections DAF and CBG linked together with member AB.
678
01:03Prediction Intervals
3.4K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
3.4K
01:22Machines: Problem Solving I
727
A toggle clamp is a mechanical device commonly used for holding and clamping objects in various applications, such as woodworking, metalworking, and assembly operations. Consider a toggle clamp subjected to a force of 200 N at the handle. The vertical clamping force can be calculated, provided the dimensions of the toggle clamp are known.
The toggle clamp system is a machine structure consisting of movable, pin-connected multi-force members that form a stabilized system to transmit forces. The...
The toggle clamp system is a machine structure consisting of movable, pin-connected multi-force members that form a stabilized system to transmit forces. The...
727