A neural network-based approach in predicting consumers' intentions of purchasing insurance policies

Insurance is a crucial mechanism used to lighten the financial burden as it provides protection against financial losses resulting from unexpected events. Insurers adopt various approaches, such as machine learning, to attract the uninsured. By using machine learning, a company is able to tap into the wealth of information of its potential customers. The main objective of this study is to apply artificial neural networks (ANNs) to predict the propensity of consumers to purchase an insurance policy by using the dataset from the Computational Intelligence and Learning (CoIL) Challenge 2000. In addition, this study also aims to identify factors that affect the propensity of customers to purchase insurance policies via feature selection. The dataset is pre-processed with feature construction and three feature selection methods, which are the neighbourhood component analysis (NCA), sequential forward selection (SFS) and sequential backward selection (SBS). Sampling techniques are carried out to address the issue of imbalanced class distributions. The results obtained are found to be comparable with the top few entries of the CoIL Challenge 2000, which shows the efficiency of the proposed model in predicting consumers’ intention of purchasing insurance policies