Machine learning in estimating operational risk coverage capital of banks with a loss distribution Approach

Article Type:
Research/Original Article (دارای رتبه معتبر)
Operational risk is one of the most important risks of financial institutions. After the approval of the Basel committee, it has started to be noticed all over the world. The increasing increase in operating losses in various business lines has caused the attention of financial institution managers to be directed to the area of operational risk. In this  research, a method for estimating the appropriate threshold for  operational loss data and also a method for classifying operational loss data is presented, and the capital required to cover operational risk by combining the intensity distribution function and frequency of operating loss data and Monte Carlo simulation are obtained. Also, the dependence between matrix cells of business lines and loss making events has also been investigated. For this research, operational loss data related to a banking group including several Asian, European and American banks have been used. The research results indicate that the loss distribution approach with the combination of critical value theory and machine learning algorithms (clustering), as well as the loss distribution approach with the combination of machine learning algorithms (classification), is more efficient than other methods.
Financial Management Perspective, Volume:13 Issue: 42, 2023
9 to 34  
دانلود و مطالعه متن این مقاله با یکی از روشهای زیر امکان پذیر است:
اشتراک شخصی
با عضویت و پرداخت آنلاین حق اشتراک یک‌ساله به مبلغ 1,390,000ريال می‌توانید 70 عنوان مطلب دانلود کنید!
اشتراک سازمانی
به کتابخانه دانشگاه یا محل کار خود پیشنهاد کنید تا اشتراک سازمانی این پایگاه را برای دسترسی نامحدود همه کاربران به متن مطالب تهیه نمایند!
  • حق عضویت دریافتی صرف حمایت از نشریات عضو و نگهداری، تکمیل و توسعه مگیران می‌شود.
  • پرداخت حق اشتراک و دانلود مقالات اجازه بازنشر آن در سایر رسانه‌های چاپی و دیجیتال را به کاربر نمی‌دهد.
In order to view content subscription is required

Personal subscription
Subscribe for 70 € euros via PayPal and download 70 articles during a year.
Organization subscription
Please contact us to subscribe your university or library for unlimited access!