Developing an Intelligent Machine Learning Model for Accurate Prediction of Employee Turnover

Employers face serious problems with employee turnover, which impacts expenses, morale, and production. Businesses can identify at-risk personnel and set protective maintenance initiatives into place by accurately forecasting turnover. The objective is to create a precise employee turnover prediction model by combining to help businesses identify at-risk workers and strengthen maintenance tactics, the model aims to maximize feature selection and increase the precision of prediction. The dataset was collected from an open-source and the data was pre-processed using min-max normalization. The novel Barnacles mating optimized Intelligent Logistic regression (BMO-ILR) approach was used to predict employee turnover. By refining choosing attributes and parameter estimation, the BMO-ILR model achieved better accuracy in forecasting staff departures, greatly outperforming conventional methods. The proposed (BMO-ILR) method achieved a better outcome of 96% accuracy, 92% precision, 99.1% recall, and 95% f1-measure, when compared with the existing methods. This method presents a more effective and exact solution for attrition estimation, allowing firms to optimize retention initiatives proactively and reduce departure.