Completion Date
Fall 2-21-2025
Document Type
Thesis
Degree Name
Master of Science (MS)
Program or Discipline Name
Information Systems Engineering and Management
Abstract
As the finance sector continues to evolve, traditional risk assessment methods struggle to calculate default risk and identify nonlinear relationships accurately. This research examines an alternative risk assessment model designed to estimate credit risk more accurately and efficiently in the credit processes of individual customers, which are one of the primary sources of income for the banking sector. It presents the theoretical design of an AI-based model. The use of this AI model can reduce human error in processes, improve risk assessment accuracy, and expedite procedures. The study adopts a postpositivist worldview and employs a quantitative research design. Algorithms including Logistic Regression, Gradient-Boosting Algorithms, Decision Trees, Random Forests, Support Vector Machines, and Neural Networks are compared. An ensemble model using XGBoost was chosen to enhance accuracy in risk prediction by addressing the model's weaknesses through a boosting technique. Cross-validation techniques are proposed to ensure high accuracy on unseen datasets and verify model reliability. The performance evaluation framework for the model, including performance metrics, is also established. Python is the primary tool used in the study, employing the NumPy, Pandas, Matplotlib, and Sklearn libraries for the data preprocessing and analysis phase. The development phase is also planned to utilize Python with TensorFlow and PyTorch libraries. In conclusion, the research evaluates the feasibility and potential of artificial intelligence in credit risk assessment, demonstrating its ability to enhance accuracy and operational efficiency while overcoming human limitations in traditional methods. It details the theoretical design of an AI-based model, serves as a guide for future work, and offers recommendations for practical applications in the banking sector.
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 4.0 International License.
Recommended Citation
Baglarbasi, E. (2025). Utilizing AI for Improved Credit Risk Assessment. Retrieved from https://digitalcommons.harrisburgu.edu/dandt/61
Included in
Management Information Systems Commons, Systems Engineering Commons, Technology and Innovation Commons