Enhancing employee performance assessments through the integration of artificial and emotional intelligence

Handling diverse and noisy behavioral data, such as everyday activities, emotional states, and interactions, is a significant problem in predicting employee success. It is challenging for traditional models to produce precise and trustworthy predictions because of the variability and inconsistencies these factors introduce. A novel Osprey Optimization Algorithm-Enhanced Decision Tree (OOA-EDT) is used to solve this problem, utilizing cutting-edge optimization techniques to improve predictive efficiency and accuracy. It makes use of an employee-based dataset that has been carefully selected to highlight performance-related elements and record important behavioural insights that affect workplace efficiency. This dataset offers a comprehensive picture of employee performance by encompassing a wide range of variables, such as work habits, communication styles, and task completion rates. Preprocessing approaches include handling missing variables and using Min-Max normalization to assure standardized inputs, eliminate bias, and improve model output consistency. Latent Semantic Analysis (LSA), a dimensionality reduction method that finds significant patterns and correlations within the dataset, is used to do feature extraction to further improve data representation. LSA improves the model's capacity to identify hidden correlations by removing the most pertinent features, which eventually raises prediction accuracy while lowering computational costs. The proposed OOA-EDT method is used for prediction of employee performance; OOA enhances the efficiency of the DT by ensuring faster convergence to optimal solutions. Experimental findings demonstrate that the OOA-EDT model outperforms conventional approaches, achieving an accuracy (97.23%), F1 score (98.18%), precision (98.75%), and recall (97.68%). These results indicate the model's effectiveness in providing accurate, reliable predictions and enhancing decision-making and employee engagement. Thus, the research significantly improves employee performance predictions and fosters a positive work environment.