EUVIMEDEUVIMED entdecken
Crossref

Next-Gen Risk Frameworks ML Integration for Credit Monitoring and Governance

Mohan Kumar Sonne Gowda

International Journal of Humanities and Information Technology · 20.03.2026 · 8 (1) · 180-187

DOI: 10.21590/ijhit.08.01.23 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Humanities and Information Technology, online erschienen am 20.03.2026. Verfasst von Mohan Kumar Sonne Gowda.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The existing traditional credit risk systems are falling short of what Basel III/IV and FINOS v2.0 require and predicted increases in non-performing loans by 2025 will only add to these concerns. This paper outlines a Hybrid machine learning (ML) - Blockchain framework that uses Ensemble (XGBoost-LSTM) to create predictions, SHAP for explainability, and Polygon Smart Contracts for a secure audit trail. By leveraging this Hybrid machine-learning-block chain model to create Rapid Probability of Default (PD) scores at a significantly reduced cost than traditional models, the proposed solution will address current limitations in the way credit risk has been historically monitored, particularly with respect to Basel III/IV and FINOS v2.0. The empirical back testing results of this research, which analyzed over 5 Million loans, demonstrated dramatic improvements in the number of loans examined (increased recall) and in the reduced number of false positives compared to the traditional credit risk monitoring processes. Additionally, the use of Blockchain Oracles enables more efficient KYC and compliance processes, while Micro-batching has addressed the issues with Real-Time Processing and produces significant cost savings associated with monitoring credit risk. This Hybrid machine learning-blockchain framework is poised to establish new standards for Credit Monitoring by 2026. Future developments of Quantum Computing and Federated Learning may lead to additional advancements over the next decade.

Zitieren

APA

Gowda, M. K. S. (2026). Next-Gen Risk Frameworks ML Integration for Credit Monitoring and Governance. International Journal of Humanities and Information Technology, 8(1), 180-187. https://doi.org/10.21590/ijhit.08.01.23

Vancouver

Gowda MKS. Next-Gen Risk Frameworks ML Integration for Credit Monitoring and Governance. International Journal of Humanities and Information Technology. 2026;8(1):180-187. doi:10.21590/ijhit.08.01.23

BibTeX
@article{Gowda2026,
  author = {Gowda, Mohan Kumar Sonne},
  title = {Next-Gen Risk Frameworks ML Integration for Credit Monitoring and Governance},
  journal = {International Journal of Humanities and Information Technology},
  year = {2026},
  volume = {8},
  number = {1},
  pages = {180--187},
  doi = {10.21590/ijhit.08.01.23}
}
Kostenlos starten →