Year: 2023
Type: article
Abstract: The assessment of credit risk is essential to contemporary economies. Historically, statistical techniques and manual auditing have been used to measure credit risk associated with credit grants. Recent developments in financial AI are the result of a new generation of machine learning (ML)-driven credit risk models that have drawn a lot of interest from both business and academia. In this research, we aimed to improve ML algorithms' performance by optimizing hyperparameters. Also, we proposed a novel multi-stage heterogeneous stacked ensemble ML algorithm for predicting credit risk. Experimental results show a significant improvement in the performance of the proposed algorithm as compared to other hyperparameter-optimized ML algorithms. Two real-time data sets from emerging market economies are used to evaluate our model. Different evaluation metrics, namely precision, recall, f1-score and accuracy, are used for evaluating model performance.
Authors: Pavitha N, Shounak Sugave
Institution: MIT World Peace University
Language: English
Subfield: Accounting
Domain: Social Sciences
Open Access status: bronze
OpenAlex ID: W4375867006