System and neural network analysis of intent to buy and willingness to pay insurance premium

Abstract

Purpose The purpose of this paper is to analyze significant determinants to assess the probability of insureds’ intent to buy (ITB) insurance and willingness to pay (WTP) quantum of dollars for security benefits. Design/methodology/approach The authors use the Double Hurdle Model (DHM) and Neural Network (NN) architecture to analyze the insureds’ behavior for ITB and WTP. The authors apply these frameworks to all the 503 insureds of a branch of a leading insurer in the United Arab Emirates. Findings The DHM identified age, loans & liabilities, body mass index, travel outside the UAE, salary and country of origin (Middle Eastern and African) as significant determinants to predict WTP for social security benefits. In addition to these determinants, NN architecture identified insurance replacement, holding multiple citizenship, age of parents, mortgages, country of origin: Americas, length of travel, income of previous year and medical conditions of insured as additional important determinants to predict WTP for social security benefits; thus, NN is found to be superior to DHM due to its lowest RMSE and AIC in the holdout sample and also its flexibility and no assumptions unlike econometric models. Research limitations/implications Insureds’ data used from one UAE Branch limit the generalizability of empirical findings. Practical implications The study findings will enable the insurers to appropriately design the insurance products that match the insurers’ behavior of ITB and WTP for social security benefits. Social implications The study findings have the potential for insurance institutions to be more flexible in their insurance practices through public–private partnerships. Originality/value This is the authors’ original research work.