An Artificial Intelligence-Based Approach to Model User Behavior on the Adoption of E-Payment

Abstract

The growth of internet usage during the COVID-19 pandemic creates a new business avenue on e-payment for organizations to expand their business horizon. However, challenges on user-related factors arise with this new avenue. This study aims to investigate the association of these factors on the adoption of e-payment services using machine learning inference. An artificial intelligence-based analysis pipeline is established to study the impact of individual items of the dependent factors on the usage of e-payment. In the analysis pipeline, the important items were extracted using a hybrid artificial intelligence method, and the relationships of these items were inferred using the tree algorithm. The results show that items related to expectancy, facilitating conditions, user attitude, and performance expectancy affect usage of e-payment services. Participants below 25 years old require a gamification solution to adopt e-payment, and participants above 40 years old need social support.