Predicting Youth Financial Inclusion: A Machine LearningClassification Approach Using Access, Quality, and Demographic Determinants

Financial inclusion has become a cornerstone of inclusive growth in India, yet its outreach ‎among youth remains uneven and underexplored. This study measures the determinants of ‎financial inclusion among the youth of Kutch district by applying both Logistic Regression ‎and Chi-square Automatic Interaction Detection (CHAID) models. The analysis is based on ‎primary data collected from 410 respondents across diverse demographic and occupational ‎backgrounds. The logistic regression model achieved an overall prediction accuracy of 90.2% ‎and a Nagelkerke R² value of 0.805, signifying strong explanatory power. The findings reveal ‎that Access and Quality dimensions—derived from the Reserve Bank of India’s Financial ‎Inclusion framework—are the most significant predictors of inclusion. Occupation and ‎income also exhibit meaningful influence, indicating that employment and financial capability ‎enhance formal participation. The CHAID model further validates these results, uncovering ‎hierarchical relationships between access, quality, and socio-economic variables. The ‎combined interpretation of both models provides a comprehensive view of youth inclusion ‎behavior and highlights that accessibility, service quality, and economic opportunity jointly ‎determine inclusion outcomes. The study concludes with policy recommendations aimed at ‎strengthening digital availability, improving service reliability, and promoting youth ‎employment to accelerate financial inclusion in semi-urban and rural India‎.