EUVIMEDEUVIMED entdecken
Crossref

ARTIFICIAL INTELLIGENCE MODELS USED IN CREDIT RISK PREDICTION

Ramil Shahin Mammadov, Sadiq Faig Isgandarli, Nijat Arif Malikov, Kanan Meheddin Mustafazade, Sabina Natig Samed-zade

Elmi Əsərlər · 2025

DOI: 10.61413/fqgv3089 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Elmi Əsərlər, 2025. Verfasst von Ramil Shahin Mammadov und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial intelligence (AI) models are making a significant contribution to improving the accuracy, efficiency, and decision-making of credit risk prediction in modern financial institutions. Traditional credit risk assessment is largely based on statistical methods such as logistic regression, which, while effective in certain cases, have limitations in identifying complex and nonlinear relationships between financial data. Artificial intelligence methods such as machine learning (ML) and deep learning (DL) provide more advanced forecasting capabilities due to their ability to process large data sets and detect complex patterns. Machine learning models such as decision trees, random forests, gradient boosting machines (GBM), and support vector machines (SVM) are widely used in modern credit scoring systems. Deep learning models, especially neural networks, provide higher accuracy in credit risk assessment with their ability to learn from highdimensional data and detect hidden correlations that traditional models cannot identify. Artificial intelligence-based credit risk prediction not only enables more accurate risk assessment, but also reduces credit default rates and increases financial inclusion based on non-traditional credit criteria. However, along with the application of these technologies, important ethical and legal issues arise, such as data privacy, model explainability and potential bias. For this reason, regulators and financial institutions implement strict controls and regulations to ensure that AI-based credit scoring systems comply with transparency, fairness and ethical standards.

Zitieren

APA

Mammadov, R. S., Isgandarli, S. F., Malikov, N. A., Mustafazade, K. M., & Samed-zade, S. N. (2025). ARTIFICIAL INTELLIGENCE MODELS USED IN CREDIT RISK PREDICTION. Elmi Əsərlər. https://doi.org/10.61413/fqgv3089

Vancouver

Mammadov RS, Isgandarli SF, Malikov NA, Mustafazade KM, Samed-zade SN. ARTIFICIAL INTELLIGENCE MODELS USED IN CREDIT RISK PREDICTION. Elmi Əsərlər. 2025. doi:10.61413/fqgv3089

BibTeX
@article{Mammadov2025,
  author = {Mammadov, Ramil Shahin and Isgandarli, Sadiq Faig and Malikov, Nijat Arif and Mustafazade, Kanan Meheddin and Samed-zade, Sabina Natig},
  title = {ARTIFICIAL INTELLIGENCE MODELS USED IN CREDIT RISK PREDICTION},
  journal = {Elmi Əsərlər},
  year = {2025},
  doi = {10.61413/fqgv3089}
}
Kostenlos starten →