Study on Mobile wallet preference in times of the COVID-19 pandemic with special reference to Pondicherry state

In the last decade, ownership and use of mobile phone has increased dramatically in India promoting the use of mobile wallet service, especially among the adults. Mobile wallet adoption and usage is poised for major growth in the next few years, and thereby displace traditional payments such as cash and cards. The COVID-19 pandemic has accelerated the trend to use mobile payment. During this study, the essential variables of technology accepted model (TAM), viz. perceived security, social influence, and perceived innovativeness, have been identified through the survey. These variables area unit expected to own associate influence on the mobile services adoption intention. The goal of this paper is to predict the adoption of mobile wallet using 5 different classifiers namely Logistic Regression (LR), Multilayer Perceptron (MLP), Random Forest (RF), Naïve Bayesian and Logistic Model Tree (LMT) classification algorithm. We assessed the classifiers of the samples collected from 100 respondents from Puducherry India.. For experimentation, WEKA is used as a simulation tool; the results reveal that the RF achieves better performance when compared to other classifiers. LR attains the classification accuracy of 78.11%, Naive Bayes 63.88%, LMT 81.5% and MLP 82.66% for the dataset respectively.