A credit approval system requires deciding approval or rejection the application for supply credit cards based on some personal data of the applicant. In this paper, based on a data sample of 690 applications from the past for credit card requests, we build a predictor model by using a Deep Learning Toolbox 14.0 in Matlab. In the model's description, detailed analysis, and correction of the input data was carried out, the model was implemented taking into account the structure, training, and testing of the deep neural network. Produced binary classifier could be used for many tasks needful to divide data in two classes by some criteria. Neural networks with different numbers of hidden layers are tested to find the best model for the prediction of credit card approval.
CITATION STYLE
Markova, M. (2021). Credit card approval model: An application of deep neural networks. In AIP Conference Proceedings (Vol. 2321). American Institute of Physics Inc. https://doi.org/10.1063/5.0040744
Mendeley helps you to discover research relevant for your work.