A Novel Hybrid ANFIS-NARX and NARX-ANN Models to Predict the Profitability of Egyptian Insurance Companies

Abstract

The use of fuzzy logic models with machine learning (ML) models have become common in many areas, especially insurance field. This study aims to compare between non-hybrid models such as artificial neural network (ANN) model, nonlinear auto-regressive with exogenous inputs (NARX) model, and the following hybrid models adaptive neural fuzzy inference system (ANFIS) model, (ANFIS-NARX) model and (NARX-ANN) model to predict the profits of the insurance activity which represent the important indicator of the good performance of Egypt’s 39 insurance companies in the period from 1st January 2009 to 31 December 2022 per month. This prediction based on the following factors (net premiums (NP), reinsurance commissions (RC), net income from investments (NIFINV), net compensation (NC), commissions of production cost (CPC), general and administrative expenses (GAE),that help decision makers to make appropriate decisions. The results found that the(ANN) model is given good results compared with the following models (ANFIS), (NARX), hybrid (ANFIS-NARX) and (NARX-ANN) models according to the following prediction accuracy measures (RMSE, MAPE, MAE and Theil Inequality). The explanatory ability criterion (R2 ) was appeared (0.79, 0.61) respectively for training and testing phases in persons insurance companies. The explanatory ability also was appeared(0.83, 0.68) respectively in property insurance companies.