Authors

  • Zarnigora Hokimjonova

DOI:

https://doi.org/10.71337/inlibrary.uz.science-research.102317

Abstract

In modern nance, credit scoring serves as a critical mechanism to evaluate the borrowing potential of individuals. Traditional models, such as logistic regression, often struggle to handle complex, heterogeneous datasets at scale. Deep learning approaches, particularly CNNs, have shown considerable promise in addressing these limitations [1]. This study introduces a novel hybrid strategy that integrates Convolutional Neural Networks (CNNs) with classical machine learning algorithms. It utilizes ASCII-based 2D grayscale transformation of tabular nancial data, facilitating the application of CNNs for deep feature learning.