کنفرانس بین المللی فناوری اطلاعات و دانش

صفحه اصلی / شانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش

Revolutionizing Credit Scoring: The Synergy of Mamba State Space and CNN Models

نویسندگان :

Behnam Sabzalian¹

1- دانشگاه آزاد اسلامی واحد علوم و تحقیقات تهران

کلمات کلیدی :

Credit Scoring،MAMBA،Convolutional Neural Networks (CNNs)

چکیده :

Credit scoring is a crucial tool for financial institutions to assess the creditworthiness of individuals and businesses. However, traditional credit scoring models often struggle with the complexity and dynamics of credit card data. To address this challenge, this study proposes a novel approach that combines a 1D Convolutional Neural Network (CNN) and Mamba State Space Model to improve the accuracy of credit scoring.The proposed approach leverages the strengths of both models to capture the patterns and dynamics in credit card data. The 1D CNN extracts relevant features from the data, while the Mamba State Space Model captures the underlying structure and dynamics. By combining these two models, the proposed approach aims to achieve more accurate credit scoring predictions.The study uses the "Default of Credit Cards Clients Dataset" collected by UCI Machine Learning Repository to evaluate the performance of the proposed approach. The results show that the proposed method achieves an accuracy of 92%, which is higher than previous researches.