| Title |
Evaluating the credit risk of SMEs using artificial intelligence, financial and alternative data / |
| Translation of Title |
Mažų ir vidutinių įmonių kredito rizikos vertinimas naudojant dirbtinį intelektą, finansinius ir alternatyvius duomenis. |
| Authors |
Miliūnaitė, Laura |
| Full Text |
|
| Pages |
69 |
| Keywords [eng] |
credit risk ; small and medium-sized enterprises ; artificial intelligence ; alternative data |
| Abstract [eng] |
Small and medium-sized enterprises (SMEs) are of major importance in world economies and job creation. Financing is one of the key issues for SME development since SMEs are often considered riskier than large companies. It is argued in the literature that artificial intelligence (AI) and alternative data could increase the financial inclusion of disadvantaged groups, such as SMEs. Thus, this study aimed to compare SMEs’ credit risk prediction models incorporating alternative data with models using only traditional financial data. The dataset used in the study involved Lithuanian SMEs’ observations from the 2015-2020 period and included traditional financial data as well as alternative data such as general characteristics of the company, macroeconomic indicators and payment behaviour data. Five different AI methods were employed in the model development process. The results showed that including alternative data in credit risk prediction models can increase the prediction performance of the models compared to models that use only financial data. Variable importance analysis revealed that payment behaviour data had the most significant impact of all alternative data-based variables. |
| Dissertation Institution |
Kauno technologijos universitetas. |
| Type |
Master thesis |
| Language |
English |
| Publication date |
2023 |
