TY  - JOUR
AU  - Taj, Sher
AU  - Javed, Muhammad Danyal
AU  - Khan, Rahim
AU  - Hassan, Hina
AU  - Khan, Zahid Ullah
PY  - 2025
DA  - 2025/10/03
TI  - Quantifying Risk with AI: Models and Frameworks
JO  - ICCK Transactions on Advanced Computing and Systems
T2  - ICCK Transactions on Advanced Computing and Systems
JF  - ICCK Transactions on Advanced Computing and Systems
VL  - 1
IS  - 4
SP  - 222
EP  - 237
DO  - 10.62762/TACS.2025.142506
UR  - https://www.icck.org/article/abs/TACS.2025.142506
KW  - risk management
KW  - risk quantification
KW  - deep learning
KW  - artificial intelligence
KW  - NIST framework
KW  - proactive risk assessment
KW  - decision-making models
AB  - Artificial intelligence (AI) has become a critical tool for risk management across industries such as insurance, healthcare, business, and finance. It enables risk quantification, improves predictive accuracy, and supports decision-making in dynamic and uncertain environments. This paper examines models, methods, and frameworks for AI-based risk assessment, while addressing concerns of ethics, regulation, and explainability. Key technologies, including machine learning, deep learning, and reinforcement learning, are highlighted for their ability to transform traditional approaches by enhancing prediction, optimization, and decision processes. The second part focuses on AI-driven risk modeling techniques. Supervised learning methods such as support vector machines, random forests, and decision trees demonstrate strong predictive capacity from historical data. Unsupervised learning, including clustering methods, uncovers hidden patterns in risk datasets. Reinforcement learning is gaining prominence for adaptive risk optimization under changing conditions. Deep learning, particularly neural networks, offers significant improvements in handling large-scale data and achieving higher predictive accuracy. Finally, the paper outlines the future of AI in risk management, recognizing both its transformative potential and persistent challenges. With the rapid advancement of AI and increasing availability of big data, risk management practices are undergoing fundamental change. Yet, successful adoption requires careful attention to ethical, legal, and technological considerations. Organizations must continue to adapt to ensure that AI technologies are deployed transparently, responsibly, and to the benefit of enterprises and society as a whole.
SN  - 3068-7969
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Taj2025Quantifyin,
  author = {Sher Taj and Muhammad Danyal Javed and Rahim Khan and Hina Hassan and Zahid Ullah Khan},
  title = {Quantifying Risk with AI: Models and Frameworks},
  journal = {ICCK Transactions on Advanced Computing and Systems},
  year = {2025},
  volume = {1},
  number = {4},
  pages = {222-237},
  doi = {10.62762/TACS.2025.142506},
  url = {https://www.icck.org/article/abs/TACS.2025.142506},
  abstract = {Artificial intelligence (AI) has become a critical tool for risk management across industries such as insurance, healthcare, business, and finance. It enables risk quantification, improves predictive accuracy, and supports decision-making in dynamic and uncertain environments. This paper examines models, methods, and frameworks for AI-based risk assessment, while addressing concerns of ethics, regulation, and explainability. Key technologies, including machine learning, deep learning, and reinforcement learning, are highlighted for their ability to transform traditional approaches by enhancing prediction, optimization, and decision processes. The second part focuses on AI-driven risk modeling techniques. Supervised learning methods such as support vector machines, random forests, and decision trees demonstrate strong predictive capacity from historical data. Unsupervised learning, including clustering methods, uncovers hidden patterns in risk datasets. Reinforcement learning is gaining prominence for adaptive risk optimization under changing conditions. Deep learning, particularly neural networks, offers significant improvements in handling large-scale data and achieving higher predictive accuracy. Finally, the paper outlines the future of AI in risk management, recognizing both its transformative potential and persistent challenges. With the rapid advancement of AI and increasing availability of big data, risk management practices are undergoing fundamental change. Yet, successful adoption requires careful attention to ethical, legal, and technological considerations. Organizations must continue to adapt to ensure that AI technologies are deployed transparently, responsibly, and to the benefit of enterprises and society as a whole.},
  keywords = {risk management, risk quantification, deep learning, artificial intelligence, NIST framework, proactive risk assessment, decision-making models},
  issn = {3068-7969},
  publisher = {Institute of Central Computation and Knowledge}
}