Cornell-Citi Financial Data Science Webinar with Bruno Dupire (Bloomberg)

Description

The Cornell-Citi Financial Data Science Webinar Series continues with Bruno Dupire (Bloomberg L.P.). He will be giving a talk titled "Some Applications of Machine Learning in Finance" on Tuesday, 3/9. This webinar be held via Zoom from 5:00pm to 6:00pm EST. This event is free and welcome to all guests. Please register to receive the confirmation email with Zoom link and all details: https://cornell.zoom.us/webinar/register/WN__rx4WKFgS7yaCRqBqlgprw Note: The confirmation will come from no-reply@zoom.us. Please make sure that this email is not sent to your spam folder by accident. Abstract: Finance has always tried to make use of all available information to optimize investment decisions. The advent of efficient Machine Learning algorithms, alternative data and computational powers has deeply impacted many fields in finance. To mention a few, rotation of factors according to market regimes in factor investing, option pricing and hedging, anomaly detection, covariance matrix cleaning, transaction cost analysis. Alternative data include texts from news and tweets, supply chain data, satellite images, vessel routes, weather data, credit card transactions, geolocation data. This overflow of information opens the door to endless number crunching and apophenia. The desperate search for signal leads to overfitting and unstable relationships, so beware. As I like to say, the market is a machine made to destroy the signal! Program Agenda: 1) Bruno Dupire's Presentation 2) Q&A 3) "Lightning Talk" featuring CFEM Alumna Yumeng Ding 4) Discussion Speaker Bio: Bruno Dupire is head of Quantitative Research at Bloomberg L.P., which he joined in 2004. Prior to this assignment in New York, he has headed the Derivatives Research teams at Société Générale, Paribas Capital Markets and Nikko Financial Products where he was a Managing Director. He is best known for having pioneered the widely used Local Volatility model (simplest extension of the Black-Scholes-Merton model to fit all option prices) in 1993 and the Functional Itô Calculus (framework for path dependency) in 2009. He is a Fellow and Adjunct Professor at NYU and he is in the Risk magazine “Hall of Fame”. He is the recipient of the 2006 “Cutting edge research” award of Wilmott Magazine and of the Risk Magazine “Lifetime Achievement” award for 2008. After a Master's degree in Artificial Intelligence in 1982 and a PhD in Numerical Analysis in 1985, he has conducted in 1987-88 a study to apply Neural Nets to time series forecasting for Caisse des Dépôts et Consignations. He has been applying Machine Learning to a variety of problems in Finance and has given many lectures on the topic in the Americas, Europe and Asia over the past few years. "Lightning Talk" Info: CFEM alumna Yumeng Ding will discuss her team capstone project, which was titled, “Interpreting Machine Learning Models.” By utilizing Machine Learning interpretability models, the Cornell CFEM team, sponsored by Alliance Bernstein, explored how black-box models can be explained and evaluated in finance. The team analyzed S&P 500 constituents and explored the interpretability of some widely-used ML modes. Yumeng Ding (MFE Cornell ’20, BA Finance Fudan University‘15) is a soon-to-be analyst in Strategic Analytics at Deutsche Bank.