No abstract

In the insurance sector, a massive volume of data is being generated on a daily basis due to a vast client base. Decision makers and business analysts emphasized that attaining new customers is costlier than retaining existing ones. The success of retention initiatives is determined not only by the accuracy of forecasting churners but also by the timing of the forecast. Previous works on churn forecast presented models for anticipating churn quarterly or monthly with an emphasis on customers' static behavior. This paper's objective is to calculate daily churn based on dynamic variations in client behavior. Training excellent models to further identify potential churning customers helps insurance companies make decisions to retain customers while also identifying areas for improvement. Thus, it is possible to identify and analyse clients who are likely to churn, allowing for a reduction in the cost of support and maintenance. Binary Golden Eagle Optimizer (BGEO) is used to select optimal features from the datasets in a preprocessing step. As a result, this research characterized the customer's daily behavior using various models such as RFM (Recency, Frequency, Monetary), Multivariate Time Series (MTS), Statistics-based Model (SM), Survival analysis (SA), Deep learning (DL) based methodologies such as Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Customized Extreme Learning Machine (CELM) are framed the problem of daily forecasting using this description. It can be concluded that all models produced better overall outcomes with only slight variations in performance measures. The proposed CELM outperforms all other models in terms of accuracy (96.4).

No abstract

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.

No abstract