A Model Fusion Approach for Enhancing Credit Approval Decision Making
🤖 AI Summary
This study addresses the financial losses and trust-related risks associated with credit default in credit card approval processes by proposing a novel multi-model ensemble mechanism based on Composite Fusion Analysis (CFA). The approach integrates five pre-trained machine learning models and enhances predictive performance through an optimized fusion strategy. Experimental results demonstrate that the proposed method achieves an accuracy of 89.13% on credit approval tasks, significantly outperforming both conventional machine learning techniques and existing ensemble methods. These findings underscore the effectiveness and innovation of the CFA framework in improving decision-making accuracy within credit risk assessment.
Application Category
📝 Abstract
Credit default poses significant challenges to financial institutions and consumers, resulting in substantial financial losses and diminished trust. As such, credit default risk management has been a critical topic in the financial industry. In this paper, we present Combinatorial Fusion Analysis (CFA), a model fusion framework, that combines multiple machine learning algorithms to detect and predict credit card approval with high accuracy. We present the design methodology and implementation using five pre-trained models. The CFA results show an accuracy of 89.13% which is better than conventional machine learning and ensemble methods.
Problem
Research questions and friction points this paper is trying to address.
credit default
credit approval
risk management
financial loss
decision making
Innovation
Methods, ideas, or system contributions that make the work stand out.
Combinatorial Fusion Analysis
model fusion
credit approval
machine learning ensemble
default prediction
🔎 Similar Papers
No similar papers found.
