Adaptive ML Framework for Predicting Digital Payment Acceptance Among Retail Merchants

1Palliboyana Shweta Ravi , 2G Chandrakala
1PG Scholar, 2Assistant Professor, Deparment of CSE ,
Sree Rama Engineering College,Tirupati,517520.
Shwetaravi67@gmail.com ,chandrakala@sreerama.ac.in

Abstract:The purpose of this project is to use machine learning techniques to forecast the adoption of digital payment systems by retail retailers. We polled 270 merchants, mostly from small and medium-sized enterprises (SMEs), from 10 of Bangalore's most popular retailmarketplaces. The study uses SVM, exploratory factor analysis, and multiple regression to identify three important adoption drivers: perceived usefulness, social effect, and compatibility. The results show that perceived social effect and usefulness are the most significant factors, whereas perceived technical support and simplicity of use are very irrelevant. Results from applying the SVM model to forecast platform adoption were only somewhat accurate. The study evaluates customer satisfaction with various digital payment methods and uses ARIMA models to forecast future trends. The study's findings will likely influence companies' strategies for accepting digital payments.
Keywords- Digital payment adoption, retail vendors, machine learning, exploratory factor analysis, support vector machine, ARIMA.