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