Arithmetic Optimization with Ensemble Deep Learning SBLSTM-RNN-IGSA model for Customer Churn Prediction

Companies in a wide variety of industries use the customer churn prediction (CCP) process to keep their current clientele happy. Insurance companies need be able forecast enhance potency and functionality deep learning methods. Deep techniques have significant impact on improving forecasting retention. Numerous studies employ standard machine Learning strategies retention, despite fact that these number accuracy issues. In light this need, piece is dedicated development stacked bidirectional long short-term memory (SBLSTM) RNN model for arithmetic optimisation algorithm (AOA) CCP. The proposed AOA-SBLSTM-RNN intends proficiently occurrence Customer Churn industry. Initially, AOA performs pre-processing transform original data into useful format. addition, SBLSTM-RNN used distinguish between churning non-churning customers. To improve CCP outcomes model, an optimal Hyperparameters tuning using Improved Gravitational Search Optimization Algorithm (IGSA) study. work, Three Health datasets were evaluate performance, four sets experiments conducted. Measures true churn, false specificity, precision, are employed assess efficacy approach. Experimental result shows Ensemble with IGSA produces value 97.89% 97.67% dataset 2 1. which better had higher predictability levels compared all other models.