Calculation of Risk Weighted Assets (RWA) via Machine Learning Technique
DOI:
https://doi.org/10.17010/ijcs/2017/v2/i6/120439Keywords:
A-IRB
, Deep Learning, F-IRB (IRB – Internal Rating Based Methodology), ML (Machine Learning), Risk Weighted Assets (RWA)Manuscript received October 5
, 2017, revised October 14, accepted October 15, 2017. Date of publication November 6, 2017.Abstract
RWAs have limited literature and confidence in reported RWAs is ebbing. Market participants question the reliability and comparability of capital ratios, and contend that banks may not be as strong as they are portrayed by risk-based capital ratios. With this paper, an altogether new idea was proposed to calculate RWA across banking industries. Machine learning approach will strengthen its calculation engine and make it more robust over time. It will predict the required RWAs on the basis of historical data and expectation feeds. As we know, machine learning is the vital concept of 21st century and can be harnessed in finance domain for evaluation of various risk attributes dynamically and can be tested in normal as well as stressed conditions.Downloads
Downloads
Published
How to Cite
Issue
Section
References
V. Lesle and S. Avramova, “Revisiting Risk Weighted Assets: Why do RWAs differ across countries and what can be done about it?†IMF Working Paper, Section III and Section IV, pp. 6–25, WP/12/90. [Online] Available: https://www.imf.org/external/pubs/ft/wp/2012/wp1290.pdf
Basel Committee on Banking Supervision, "International Convergence of Capital Measurement and Capital Standards, A revised framework comprehensive version," Bank for International Settlements, Revised Basel III publication in 2017, Section(s) - Part 2: I B, pp 12; Part 2: II, pp. 19-51; Part 2: III, pp. 52-119, June 2006 - December 2017 [Online] Available: 1. http://www.bis.org/publ/bcbs128.pdf (original), 2. https://www.bis.org/bcbs/publ/d424.pdf (final)
S. Chatterjee, Center for Central Banking Studies – Handbook No. 34 – Modelling Credit Risk. UK: Centre for Central Banking Studies, Bank of England, Section 1: pp. 5-12, 2015 [Online] Available: https://www.bankofengland.co.uk/-/media/boe/files/ccbs/resources/modelling-credit-risk.pdf
Microsoft Azure, "Exemplary workspace for training and solution," 2017. [Online] Available: https://docs.microsoft.com/en-us/azure/machine-learning/machine-learning-walkthrough-develop-predictive-solution
N. D. Lewis, “Deep Learning Made Easy with R: A Gentle Introduction for Data Science,†CreateSpace Independent Publishing Platform, January 10, 2016
