Employee performance prediction model in large scale organizations based on Extreme Learning Machine

The advancement of artificial intelligence in predicting employee performance using data has considerably enhanced the efficiency of human resource management and organizational decision-making. Traditional methods for evaluating employee performance, such as Key Performance Indicators (KPIs) and the ۳۶۰-degree evaluation system, often prove insufficient in capturing the complexity of employee data and the multidimensional aspects of performance. In this study, we introduce a novel employee performance prediction model based on Extreme Learning Machine (ELM), designed to accurately forecast employee performance by automatically capturing complex and nonlinear patterns within the data. The proposed model is evaluated using the publicly available Employee Performance Dataset, which comprises comprehensive records of employee attributes and performance metrics, making it suitable for assessing the effectiveness of the ELM-based predictive framework. The results of the performance prediction demonstrate that, in comparison with conventional evaluation methods, the ELM-based model substantially enhances the accuracy and reliability of employee performance prediction across multiple performance dimensions. These findings indicate that the ELM approach offers a more efficient and robust alternative to existing predictive models for employee performance assessment. Furthermore, the study confirms the practical feasibility of applying ELM for performance prediction and highlights its potential to provide more effective decision-support tools for human resource management across diverse industries.

کلیدواژه ها:

Extreme Learning Machine ، Employee Performance Prediction ، Human Resource Management ، Model Interpretability ، Data-Driven Decision Making