A two-staged SEM-neural network approach for understanding and predicting the determinants of m-commerce adoption

The advancement in wireless and mobile technologies has presented tremendous business opportunity for mobile-commerce (m-commerce). This research aims to examine the factors that influence consumers’ m-commerce adoption intention. Variables such as perceived usefulness, perceived ease of use, perceived enjoyment, trust, cost, network influence, and variety of services were used to examine the adoption intentions of consumers. Data was collected from 376 m-commerce users. A multi-analytic approach was proposed whereby the research model was tested using structural equation modeling (SEM), and the results from SEM were used as inputs for a neural network model to predict m-commerce adoption. The result showed that perceived usefulness, perceived enjoyment, trust, cost, network influence, and trust have significant influence on consumers’ m-commerce adoption intentions. However, the neural network model developed in this research showed that the best predictors of m-commerce adoption are network influence, trust, perceived usefulness, variety of service, and perceived enjoyment. This research proposed an innovative new approach to understand m-commerce adoption, and the result for this study will be useful for telecommunication and m-commerce companies in formulating strategies to attract more consumers.

► The determinants of m-commerce adoption were examined in this research.
► The TAM model was extended by incorporating perceived enjoyment, trust, cost, network influence, and variety of services.
► A two-staged, multi-analytic approach of integrating SEM and neural network was applied to examine the model.
► The multi-analytic approach addressed existing limitations in applying SEM or neural network individually.
► Result showed that perceived usefulness, perceived ease of use, perceived enjoyment, trust, cost, variety of services, and network influence m-commerce adoption.
► The integrated approach allows more accurate results that help decision makers develop appropriate strategies to improve m-commerce adoption.