Credit scoring using machine learning algorithms : microfinance for capital aid and employment of the poor | |
| Author | Nguyen Duc Doanh |
| Call Number | AIT Project no.PMDS-22-04 |
| Subject(s) | Credit scoring systems Machine learning Credit ratings--Vietnam |
| 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-22-04 |
| Abstract | Over the past time, financial institutions and banks across the world need to have been implementing credit scoring solutions to minimize risks in lending money. But in Vietnam, there are still a lot of credit institutions and banks that are using paper and human processes to score credit, which leads to great risks due to human subjectivity and lack of savings. cost savings. This study explored the use of machine learning models used for credit scoring purposes, there are many models that give pretty good results but need to invest a lot of money for testing, implementing and operations, such as models Logistic Regression-feature groups, Decision Tree Classifier-feature groups, Random Forest Classifier-feature groups, XGBoost-EBCA, Bstacking-XGBoost-MV, Consensus model and Cluster-based consensus model. Then an experiment was conducted on the CEP organization's dataset with machine learning algorithms and compared with models: Logistic Regression, KNeighbors Classifier, Support Vector Machine, Decision Tree Classifier, Bagging Classifier, Random Forest Classifier and Gradient Boosting Classifier. Our main result is that (1) Random Forest Classifier model and Gradient Boosting Classifier model are the best, but (2) KNeighbors Classifier model has certain advantages and (3) Support Vector Machine the proposed model is perfect fully meet the requirements. Our model is quite simple, easy to implement, and low operating costs will help to quickly deploy to small financial institutions in Vietnam taking advantage of machine learning models in credit scoring, including CEP. |
| Year | 2022 |
| Corresponding Series Added Entry | Asian Institute of Technology. Project ; no. PMDS-22-04 |
| 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) | Chaklam Silpasuwanchai; |
| Examination Committee(s) | Chutiporn Anutariya;Vatcharaporn Esichaikul; |
| Degree | Professional Master in Data Science and Artificial Intelligence Applications - Asian Institute of Technology, 2022 |