To explore the influencing factors of the adoption of mobile payment systems\nfrom the perspective of merchants, this study builds a data analysis model\nbased on three different ensemble learning algorithms, Adaboost model,\nrandom forest and XGBoost model, where static social-economic attributes,\ndynamic trading behavior and clustering effect variables of merchants are\nused as independent variables. Moreover, this paper establishes the prediction\nmodels and analyzes the prediction accuracy of different models. The results\nof the study indicate that: 1) Merchants in the housing industry, health hospitals\nand retail industries are more willing to adopt mobile payment systems;\n2) The average daily transaction volume and the average amount of each\nconsumer significantly affect the merchant mobile payment adoption behavior;\n3) The adoption of mobile payment systems by neighboring merchants\nsignificantly positively affected the adoption behavior of merchants; 4) On\nthe basis of the social-economic attributes of merchants, the hit rate and accuracy\nof the prediction model were greatly improved after adding transaction\ndata.
Loading....