Predictive Analysis of Optimal Automated Teller Machine Site Selection Using Machine Learning and Deep Learning: A Comprehensive Study on Variables, Challenges, and Opportunities

The proliferation of Automated Teller Machines (ATMs) in the banking sector has raised the stakes in identifying the most suitable locations for these machines, given their impact on the profitability and satisfaction of bank clients. This study presents a comprehensive examination of the variables that influence ATM placement, exploring the significance of identifying an optimal location and the challenges associated with this task. Our investigation pivots on market-centric variables such as the proximity of eateries, fuel stations, that are ubiquitously available in the public domain. To establish this benchmark, a dataset that remains singularly unique and is conspicuously absent from publicly accessible Internet repositories is created. Our innovative approach encompasses the application of multiple machine learning models to analyze the performance using unprecedented dataset. This study also focuses on ranking the market factors that we used in the novel dataset to study what market variables affect the location of an ATM along with resolving the limitations and challenges.