An Efficient Classification Algorithms for Prediction of Employee Performance Based on Mask Rcnn-Bilstm Technique

Companies that focus on operational effectiveness value the productivity and efficiency of their workers. When productivity goes up at one level, it often spreads to other levels of the organisation, which increases output. So, you need to check on your employees' work periodically. There isn't just one thing that affects how productive a person is, therefore a structured, data-driven plan is needed. This study shows a step-by-step methodology that includes data preprocessing, feature selection, and model training. Preprocessing makes data that isn't useful or informative for analysis useful and informative. Intensive Optimised Principal Component Analysis (PCA) is recommended for feature selection since it keeps important information while minimising dimensionality. Model training combines MaskRCNN's ability to recognise space with BiLSTM ability to learn over time. This combination may appear oldfashioned compared to newer standalone methods, yet it works effectively here. The model's 98.65 % accuracy made it easier to forecast and evaluate how well employees were doing. These results suggest that the proposed framework can help businesses keep an eye on and increase the efficiency of their workers using advanced, automated technologies.