Using deep neural network for credit scoring model development | |
| Author | Nguyen Huu Phong |
| Call Number | AIT Project no.PMDS-22-07 |
| Subject(s) | Credit scoring systems Neural networks (Computer science) Deep learning (Machine learning) Credit ratings |
| Note | A project study submitted in partial fulfillment of the requirements for the degree of Professional Master in Data Science and Artificial Intelligence Applications, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Project ; no. PMDS-22-07 |
| Abstract | The history of credit scoring dates back to the 1950s (Xolani Dastile et al., 2020). It is a critical task for risk management. The models have been developed by variety of approaches, from statistical models to more complicated DNN models. In this project, I focused on build DNN models to solve credit scoring problem, particularly CNN. The CNN architectures were built on my organization's dataset which is tabular type. The data were transformed to images, then apply CNN architectures. Compared to other models, the CNN model produced a better outcome. Additionally, the model uses SHAP to explain. |
| Year | 2022 |
| Corresponding Series Added Entry | Asian Institute of Technology. Project ; no. PMDS-22-07 |
| Type | Project |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Professional Master in Data Science and Artificial Intelligence Applications (PMDS) |
| Chairperson(s) | Dailey, Matthew N.; |
| Examination Committee(s) | Chaklam Silpasuwanchai;Chutiporn Anutariya; |
| Degree | Professional Master in Data Science and Artificial Intelligence Applications - Asian Institute of Technology, 2022 |