![Infopro Digital Events [EB8]](/sites/default/files/styles/site_logo/public/2020-01/RISK%20TRAINING%20LOGO-HORIZ-RGB-EB8.png?itok=c5i0WDqv){kind=logo}
Course Agenda
Agenda
Agenda: Machine Learning in Finance - Toronto
Day one: Wednesday, March 25, 2020
08:30 – 09:00
Registration and refreshments
09:00 – 10:30
Introduction to machine learning and a tour of machine learning models
-
What is machine learning?
-
Why use machine learning?
-
What are the components of machine learning?
-
Overview of machine learning methods: from naïve bayes to neural networks and deep learning
10:30 – 10:45
Morning break
10:45 – 12:00
A deeper dive into neural networks
-
Gradient descent algorithms and hyperparameters
-
Stopping rules
-
CNNs and RNNs
-
Application to volatility surface movements
John Hull
Maple Financial Professor of Derivatives and Risk Management, Joseph L. Rotman School of Management
University of Toronto
John Hull, Maple Financial Professor of Derivatives and Risk Management, Joseph L. Rotman School of Management, UNIVERSITY OF TORONTO
John Hull is an internationally recognized authority on derivatives and risk management and has many publications in this area. His work has an applied focus. In 1999 he was voted Financial Engineer of the Year by the International Association of Financial Engineers. He has acted as consultant to many North American, Japanese, and European financial institutions. He has won many teaching awards, including University of Toronto's prestigious Northrop Frye award.
12:00 – 13:00
Lunch
13:00 – 14:30
A deeper dive into reinforcement learning
-
Monte carlo vs. temporal difference algorithms
-
Simple example: the game of Nim
-
Deep Q-learning
-
Application to hedging derivative
John Hull
Maple Financial Professor of Derivatives and Risk Management, Joseph L. Rotman School of Management
University of Toronto
John Hull, Maple Financial Professor of Derivatives and Risk Management, Joseph L. Rotman School of Management, UNIVERSITY OF TORONTO
John Hull is an internationally recognized authority on derivatives and risk management and has many publications in this area. His work has an applied focus. In 1999 he was voted Financial Engineer of the Year by the International Association of Financial Engineers. He has acted as consultant to many North American, Japanese, and European financial institutions. He has won many teaching awards, including University of Toronto's prestigious Northrop Frye award.
14:30 – 14:45
Afternoon break
14:45 – 16:15
Machine learning in risk management and audit
-
Machine learning in banking, risk management & modeling
-
Classification with unbalanced data
-
Anomaly detection
-
Extracting features from networks
-
Breakout detection in time series
16:15 – 16:15
End of day one
Day two: Thursday, March 26, 2020
08:30 – 09:00
Registration and refreshments
09:00 – 10:30
A deeper dive into natural language processing
-
Reading the news quickly to get in front of the crowd
-
What are your competitors doing?
-
Identifying other players in markets
-
Assessing the reaction to events, products, and services
-
Applying language models to analyze non-linguistic data
Elliot Noma has worked in both finance and data science. He is a consultant on machine learning and natural language processing solutions at the Federal Reserve Bank of New York. He also runs a proprietary trading company, Garrett Asset Management.
Dr. Noma taught machine learning at Columbia University and currently teaches quantitative risk management in the Masters in Mathematical Finance program at Rutgers University.
Previously, Dr. Noma was a portfolio manager running a fund of hedge funds and was the Chief Risk Officer at Asset Alliance, a $3 billion seeder of hedge funds.
Prior to working at Asset Alliance, Elliot was a risk manager at both Merrill Lynch Investment Advisers and Deutsche Bank, was an analyst at both JP Morgan and Salomon Brother, and was a investment banker at Chase.
He has patented a levered ETF structure, has written a book on psychometrics, and has published scholarly articles in behavioral finance, psychology, information science, sociology, math, and finance. His most recent article in 2018 describes a new method of measuring financial risk aversion using hypothetical investment preferences.
Dr. Noma has a Ph.D. in the mathematical modeling of psychological processes from the University of Michigan along with an M.A. in Mathematics. He graduated from Dartmouth College with a B.A. in Mathematics.
10:30 – 10:45
Morning break
10:45 – 12:00
Explain yourself - the importance of explainability in finance
-
Deep learning as a current trend in machine learning
-
Challenges in leveraging state-of-the-art approaches
-
The requirement of explainable models from a regulatory perspective
-
Approaches to satisfy explainability in the financial space
12:00 – 13:00
Lunch
13:00 – 14:30
Machine learning in finance: putting it into practice
-
Pros and cons of applying ML to investing
-
Importance of features selection
-
Subtleties of applying ML to investing
-
Where to start?
Vishal Gossain is currently the vice president of global risk management responsible for all global regulatory and non-regulatory retail models, and application of artificial intelligence and machine learning for retail products. Vishal has held previous senior retail modeling, risk management, business strategy, P&L management and finance positions in Latin America and North America. Some of them include Head of credit risk for HSBC in Latin America, Head of credit risk for Capital One Canada and several other risk/business management positions in HSBC USA and consulting firms.
Vishal currently sits on the board of MIT Computer Science and Artificial Intelligence Laboratory and University of Western Post-graduate program.
Vishal holds an undergraduate degree in engineering from Indian Institute of Technology (IIT) Kharagpur and has completed his post-graduation in engineering from University of Texas at Austin.
14:30 – 14:45
Afternoon break
14:45 – 16:15
Machine learning for fraud and AML
-
Supervised and unsupervised methods
-
Signal processing
-
Regularization and dropout
-
Isolation forests
-
Algorithm selection and application
Lee Medoff is the founder and CEO of Hedgehog Analytics, a data and analytics consulting firm that provides analytics services and solutions, with the Financial Services sector a primary area of focus. The firm advises tech startups as well, including those in the FinTech sector.
Lee began his career in finance with the Decision Sciences group of the credit card division of JPMorgan Chase, where he developed models to optimize the return on the bank’s card portfolio. He then joined the Models and Methodologies group of the New York Fed, where as part of the Bank Supervision group he focused on Credit and Operational risk, reviewing the models banks in the 2nd District used for Basel, Economic Capital and Stress Testing purposes. Following the Fed he moved to Moody’s Analytics Risk Management Services, where he oversaw analytics teams in New York and India developing and customizing models for the firm’s software. He also was a consultant for the Quantitative Advisory Services Group of EY’s Financial Services Risk Management practice, where he worked on stress testing, CCAR and CECL banking and trading book projects for large US and Global financial services clients.
He holds advanced degrees in Statistics from Columbia University and Economics from New York University.
Lee enjoys reading, cycling, and all things tech and is a die-hard foodie.
16:15 – 16:15