Machine Learning and AI in Risk Management
4 likes3,452 views
The document presents a webinar on the role of machine learning and AI in risk management, featuring expert insights from Sri Krishnamurthy. It covers the evolution of finance with these technologies, benefits of machine learning for fraud detection, and the challenges of implementing AI in production environments. Key claims about machine learning's effectiveness are paired with cautions regarding data quality, model interpretability, and the need for skilled data scientists.
![19
AI and Machine Learning in Production
https://www.itnews.com.au/news/hsbc-societe-generale-run-
into-ais-production-problems-477966
Kristy Roth from HSBC:
“It’s been somewhat easy - in a funny way - to
get going using sample data, [but] then you hit
the real problems,” Roth said.
“I think our early track record on PoCs or pilots
hides a little bit the underlying issues.
Matt Davey from Societe Generale:
“We’ve done quite a bit of work with RPA
recently and I have to say we’ve been a bit
disillusioned with that experience,”
“the PoC is the easy bit: it’s how you get that
into production and shift the balance”](https://image.slidesharecdn.com/prmia-171209190500/85/Machine-Learning-and-AI-in-Risk-Management-19-320.jpg)
Machine Learning and AI in Risk Management
- 1. Location: QU-MathWorks-PRMIA Webinar 12/06/2017 Machine Learning and AI in Risk Management 2017 Copyright QuantUniversity LLC. Presented By: Sri Krishnamurthy, CFA, CAP [email protected] www.analyticscertificate.com
- 2. • Founder of QuantUniversity LLC. and www.analyticscertificate.com • Advisory and Consultancy for Financial Analytics • Prior Experience at MathWorks, Citigroup and Endeca and 25+ financial services and energy customers. • Regular Columnist for the Wilmott Magazine • Author of forthcoming book “Financial Modeling: A case study approach” published by Wiley • Charted Financial Analyst and Certified Analytics Professional • Teaches Analytics in the Babson College MBA program and at Northeastern University, Boston Sri Krishnamurthy Founder and CEO 2
- 3. 3 What’s it like to be a risk manager in the age of Machine Learning and AI? Source: https://imgs.xkcd.com/comics/machine_learning.png Risk Manager Trader/Quant
- 4. 4 • Machine Learning and AI in Finance ▫ A quick introduction • Machine Learning and AI: A practitioner’s perspective ▫ 5 things every Risk manager should know about Agenda
- 5. 5 AI and Machine Learning in the News https://www.economist.com/news/finance-and-economics/21722685-fields- trading-credit-assessment-fraud-prevention-machine-learning https://www.udacity.com/course/machine-learning-for-trading--ud501 https://www.forbes.com/sites/louiscolumbus/2017/10/23/machine- learnings-greatest-potential-is-driving-revenue-in-the- enterprise/#3fd4c2da41db https://www.cnbc.com/2017/09/28/man-group- one-of-worlds-largest-funds-moves-into-machine- learning.html
- 6. 6 • “AI is the theory and development of computer systems able to perform tasks that traditionally have required human intelligence. • AI is a broad field, of which ‘machine learning’ is a sub-category” What is Machine Learning and AI? Source: http://www.fsb.org/wp-content/uploads/P011117.pdf
- 7. 7 Machine Learning & AI in finance – A paradigm shift Stochastic Models Factor Models Optimization Risk Factors P/Q Quants Derivative pricing Trading Strategies Simulations Distribution fitting Quant Real-time analytics Predictive analytics Machine Learning RPA NLP Deep Learning Computer Vision Graph Analytics Chatbots Sentiment Analysis Alternative Data Data Scientist
- 8. 8 The Virtuous Circle of Machine Learning and AI Smart Algorithms Hardware Data
- 9. 9 The rise of Big Data and Data Science Image Source: http://www.ibmbigdatahub.com/sites/default/files/infographic_file/4-Vs-of-big-data.jpg
- 10. 10 Smarter Algorithms Parallel and Distributing Computing Frameworks Deep Learning Frameworks 1. Our labeled datasets were thousands of times too small. 2. Our computers were millions of times too slow. 3. We initialized the weights in a stupid way. 4. We used the wrong type of non-linearity. - Geoff Hinton “Capital One was able to determine fraudulent credit card applications in 100 milliseconds”* * http://go.databricks.com/hubfs/pdfs/Databricks-for-FinTech-170306.pdf
- 11. 11 Hardware
- 16. 16
- 17. 17 Claim: • Machine learning is better for fraud detection, looking for arbitrage opportunities and trade execution Caution: • Beware of imbalanced class problems • A model that gives 99% accuracy may still not be good enough 1. Machine learning is not a generic solution to all problems
- 18. 18 Claim: • Our models work on datasets we have tested on Caution: • Do we have enough data? • How do we handle bias in datasets? • Beware of overfitting • Historical Analysis is not Prediction 2. A prototype model is not your production model
- 19. 19 AI and Machine Learning in Production https://www.itnews.com.au/news/hsbc-societe-generale-run- into-ais-production-problems-477966 Kristy Roth from HSBC: “It’s been somewhat easy - in a funny way - to get going using sample data, [but] then you hit the real problems,” Roth said. “I think our early track record on PoCs or pilots hides a little bit the underlying issues. Matt Davey from Societe Generale: “We’ve done quite a bit of work with RPA recently and I have to say we’ve been a bit disillusioned with that experience,” “the PoC is the easy bit: it’s how you get that into production and shift the balance”
- 20. 20 Claim: • It works. We don’t know how! Caution: • It’s still not a proven science • Interpretability or “auditability” of models is important • Transparency in codebase is paramount with the proliferation of opensource tools • Skilled data scientists who are knowledgeable about algorithms and their appropriate usage are key to successful adoption 3. We are just getting started!
- 21. 21 Claim: • Machine Learning models are more accurate than traditional models Caution: • Is accuracy the right metric? • How do we evaluate the model? RMS or R2 • How does the model behave in different regimes? 4. Choose the right metrics for evaluation
- 22. 22 Claim: • Machine Learning and AI will replace humans in most applications Caution: • Beware of the hype! • Just because it worked some times doesn’t mean that the organization can be on autopilot • Will we have true AI or Augmented Intelligence? • Model risk and robust risk management is paramount to the success of the organization. • We are just getting started! 5. Are we there yet? https://www.bloomberg.com/news/articles/2017-10-20/automation- starts-to-sweep-wall-street-with-tons-of-glitches
- 23. 23 A framework for evaluating your organization’s appetite for AI and machine learning Source: http://www.fsb.org/wp-content/uploads/P011117.pdf
- 24. 24 Regulators are catching up http://www.fsb.org/wp-content/uploads/P011117.pdf
- 25. 25 About us: • Data Science, Quant Finance and Machine Learning Advisory • Trained more than 1000 students in Quantitative methods, Data Science and Big Data Technologies using MATLAB, Python and R • Programs ▫ Analytics Certificate Program ▫ Fintech programs • Platform
- 26. Thank you! Sri Krishnamurthy, CFA, CAP Founder and Chief Data Scientist QuantUniversity LLC. srikrishnamurthy www.QuantUniversity.com www.analyticscertificate.com Information, data and drawings embodied in this presentation are strictly a property of QuantUniversity LLC. and shall not be distributed or used in any other publication without the prior written consent of QuantUniversity LLC. 26