With the rapid development of the personal credit market, it is accompanied by financial risks brought about by dishonesty. Among the existing personal credit prediction models, the traditional machine learning model is ineffective in dealing with multiple categories of users due to its poor generalization ability. In contrast, the neural network model requires many samples to cover multiple modal users. Its high training cost also makes this method limited. This paper proposes an adaptive iterative multimodal clustering method to predict the default of credit users. According to the multicategory characteristics of credit users, the method first divides users into multiple sets from coarse to fine-grained and then establishes decision tree models for prediction. This method not only solves the problem of the poor generalization ability of traditional machine learning models but also ensures that the overall training cost of the model is low. Comparative experiments are conducted based on representative credit datasets to verify the superiority and effectiveness of the proposed model. Experimental results show that the composite model outperforms other machine learning models and is suitable for personal credit loan prediction problems.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.