Author(s): Naresh Boora, S Sreenivasa Murthy
Employee performance prediction plays a crucial role in managing human resources effectively and optimizing organizational outcomes. This paper proposes a novel approach that combines data mining techniques with machine learning algorithms to develop an Employee Performance Prediction System (EPPS). Additionally, a self-regularized Siberian Tiger Optimization (SSTO) algorithm is introduced as a feature selection mechanism to enhance the accuracy and efficiency of the prediction system. The EPPS utilizes historical employee data, including personal attributes, work experience, training records, and performance evaluations, to build a comprehensive performance prediction model. Various data mining techniques, such as data preprocessing, feature extraction, and feature selection, are employed to refine the dataset and extract relevant features that have a significant impact on employee performance. To further improve the accuracy of the prediction model, the self-regularized SSTO algorithm is introduced as a feature selection method. Inspired by the hunting behavior of Siberian tigers, the SSTO algorithm mimics the search and optimization process to identify the most influential features for performance prediction.