Enhancing Financial Inclusion in Uzbekistan: A Machine Learning Approach to Predicting Car Loan Adoption Among Remittance Recipients
Abstract
In Uzbekistan, the adoption rate of financial services and products among remittance recipients remains relatively low. Identifying which remittance recipients are more suitable for cross-selling retail banking products is crucial. The primary objective of this study is to develop a robust model that assists financial institutions in identifying potential customers with a higher likelihood of adopting car loans. We use a unique dataset of remittance transactions and vehicle financing data obtained from a bank in Uzbekistan. We apply sampling techniques and compare the performance of different machinelearning models in these datasets. Our analysis reveals that Decision Tree and Random Forest models outperform others. We apply Shapley Additive explanations values to explain the heterogeneous impact of independent variables on outcome. The results of this study offer practical implications for financial institutions in remittance-receiving countries aiming to leverage remittance for financial inclusion.