ASSESSING PERCEIVED RISK IN MOBILE MONEY ADOPTION UNDER COVID-19: A COMBINED SEM-ARTIFICIAL NEURAL NETWORK TECHNIQUES

The introduction of social distancing measures to curb the COVID-19 pandemic and support stabilization economy has motivated consumers do contactless activities, including mobile money service (MMS). Although this remains beneficial consumers, adoption rate is still at its formative stage in Togo. socio-economic background peoples' inclination are hesitant for such rising digital transactions, seemingly due risk perception. Therefore, study develops a model capture multidimensional perceived regarding decision. A total 275 respondents were tested using hybrid structural equation modeling (SEM) artificial neural network (ANN) approach through multilayer perceptron (MLP) with feed-forward back-propagation (FFBP) algorithm. ANN found seize better performance high prediction accuracy than SEM nonlinearity linearity. Our results suggest that privacy (PRR) stands out as most critical antecedent overall (POR), which latter negatively affect behavioral intention (BI) use MMS. This research one first test acceptance MMS empirically during crisis contributes both theoretically practically toward understanding factors influencing widespread adoption. To promote citizen's trust, providers must provide instructions on safely coping breaches security problems if they arise. SEM-ANN methodology will aid fulfill current literature gap practical guidance evidence-based decision-making.