Data-Driven Exploration of Financial Literacy: A Multifactorial Approach

The financial literacy of a person determines their ability to manage finances effectively. The key determinants of financial literacy have become much more crucial today as we navigate through complex financial terrain. Therefore, this study seeks to identify and analyze the factors contributing to financial literacy through machine learning models like Decision Tree, MLP, Random Forest, and Naive Bayes. The present study used real-time data from teachers at private colleges in India. This study focused on identifying and ranking the most significant factors influencing financial literacy through Feature selection score analysis. The findings of the study stated that income, social status, age, family income, and investment experience have a significant effect on identifying financial literacy. Thus, comparative analysis of the machine learning models reveals that the Random Forest classifier outperforms others, achieving an accuracy of 95%, closely followed by the Decision Tree and MLP with 94% accuracy. Although the ‘Naive Bayes’ classifier has a much lower accuracy (59%), this shows its limitations. It is evident from the results that intricate models such as MLP and Random Forest are beneficial in highlighting detailed dimensions of factors influencing financial literacy. Therefore, it informs teachers and decision-makers who want to improve financial education programs.