The purpose of this study is to investigate the role of non-credit information in predicting less than optimal financial behaviors. In this study, we test whether individual characteristics, financial status, financial education, and financial knowledge successfully predict AFS usage by using machine learning methodologies. For the ACCI conference, we expect to expand this to credit usage in addition to AFS usage. We evaluate the performance of our machine learning model and suggest the criteria to choose the optimal models based on the prediction purposes.

Accepted Oral Presentation