Replication Data for: Credit scoring of thin file consumers

The rapid evolution of machine learning (ML) offers transformative potential for the credit scoring industry, especially in addressing the challenges faced by \"thin-file\" consumers who lack substantial credit histories. Traditional credit scoring models often fail to accurately assess these consumers due to insufficient data, leading to potential exclusion from crucial credit services. This research leverages a synthetically created dataset, generated using advanced Python libraries like Pandas, NumPy, and Faker, to develop and refine ML algorithms capable of evaluating such underserved consumer segments. The synthetic nature of the dataset ensures compliance with privacy norms while allowing the simulation of diverse consumer behaviors—from stable to erratic financial activities—typical of thin-file profiles. This initiative not only drives innovation in algorithmic credit scoring but also aligns with broader objectives of financial inclusivity, aiming to bridge service gaps by equipping the financial industry with tools to fairly evaluate creditworthiness across all consumer segments. Thus, this dataset forms a critical cornerstone for advancing research that enhances technical capabilities and fosters societal progress through improved financial inclusion.