Authors: Assistant Professor Dr.B.Sai Venkata Krishna, J. Swapna
Abstract: The rapid advancement of digital technologies has significantly transformed the retail sector by accelerating the adoption of digital payment platforms. Digital payment solutions provide enhanced transaction speed, improved security, operational efficiency, and greater convenience for both merchants and consumers. Despite these advantages, the adoption of digital payment platforms among small and medium-sized retail vendors remains inconsistent due to several technological, organizational, and behavioral factors. Understanding these influencing factors is essential for financial institutions, payment service providers, policymakers, and retailers seeking to promote a cashless economy. Recent developments in Machine Learning (ML) have enabled more effective analysis of complex adoption patterns by identifying hidden relationships within large datasets and generating reliable predictive models.. The predictive performance of the proposed framework is evaluated using Accuracy, Precision, Recall, and F1-Score metrics. Experimental analysis demonstrates that the Support Vector Machine achieves an overall accuracy of 56.67%, precision of 59.38%, recall of 66.67%, and an F1-score of 66.25%, indicating moderate predictive capability for digital payment adoption. The findings further reveal that perceived usefulness, social influence, and compatibility are the most significant factors encouraging adoption, whereas perceived ease of use and technical support exhibit relatively lower influence. The proposed framework provides valuable insights for improving digital payment adoption strategies and supports policymakers, financial institutions, and platform providers in developing more effective initiatives that encourage wider acceptance of digital payment technologies among retail vendors.
