Dynamic Behavior-Based Churn Forecasts in the Insurance Sector

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).

Systemic Financial Risk Forecasting: A Novel Approach with IGSA-RBFNN

“…Although RBFNN demonstrates excellent performance in various prediction aspects, the challenge of parameter selection for RBFNN persists [40]. The parameters of RBFNN can be optimized using various optimization algorithms such as Particle Swarm Optimization (PSO) [41], Genetic Algorithm (GA) [42], Simulated Annealing (SA) [43], and GSA [21] for neural network training. Compared to other algorithms, GSA possesses stronger global search and parallel processing capabilities, albeit with slower training speed.…”

“…The optimization is performed according to the gravitational interaction between individuals until the optimal individual is found. The optimal individual obtained from the IGSA algorithm is used to assign values to the center j C , width value σ j , and network connection weight j w of the hidden layer nodes' basis functions in RBFNN, resulting in the IGSA-RBFNN prediction model [41]. The flowchart is shown in Figure 3.…”

“…Update of the gravitational coefficient [41]. A linear function is used to improve the gravitational coefficient, and the calculation formula can be seen in Equations ( 27) and (28).…”

Arithmetic Optimization With Ensemble Deep Learning SBLSTM-RNN-IGSA Model for Customer Churn Prediction

“…[16]. Alboukaey et al [17] proposed a daily churn forecasting model that forecasts churn using actions as a multivariate period On mobile telecom data, a statistical approach, an RFM model, an LSTM model, and a CNN concept were used. Everyday churn predictions beat monthly projections, they discovered.…”