Cornell-Citi Financial Data Science Webinar with Charles-Albert Lehalle (Capital Fund Management)

Description

The Cornell-Citi Financial Data Science Webinar Series is kicking off the Spring 2021 semester with Charles-Albert Lehalle (Capital Fund Management) as our first speaker. He will be giving a talk titled "An Attempt to Understand Natural Language Processing And Illustration On A Financial Dataset" on Tuesday, 2/16. 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_AR4OJkIoTzCoNcpElkQ60w 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: I will present a theoretical analysis of word2vec language models and explain how the resulting understanding can generalize to more nonlinear ones (like BERT). This analysis relies on trying to exhibit a generative model allowing to explain the asymptotic meaning of the loss functions used by these kinds of models. In particular, it allows to produce synthetic languages having a controlled number of "synonyms" and try to learn them with standard algorithms. I will then show how learning the language of financial news reflects (or not) the celebrated Loughran-McDonald sentiment lexicon. This on-going work is conducted with Mengda Li (ENS Paris Saclay). Program Agenda: 1) Charles-Albert Lehalle's Presentation 2) Q&A 3) "Lightning Talk" about NLP featuring CFEM Alumna Silvia Ruiz 4) Discussion Speaker Bio: Currently Head of Data Analytics at Capital Fund Management (CFM, Paris) and visiting researcher at Imperial College (London), Charles-Albert Lehalle studied machine learning for stochastic control during his PhD 20 years ago. He started his career being in charge of AI projects at the Renault research center and moved to the financial industry with the emergence of automated trading in 2005. He became an expert in market microstructure and has been appointed Global Head of Quantitative Research at Crédit Agricole Cheuvreux, and Head of Quantitative Research on Market Microstructure in the Equity Brokerage and Derivative Department of Crédit Agricole Corporate Investment Bank after the crisis. He provided research and expertise on these topics to investors and intermediaries, and is often heard by regulators and policy-makers like the European Commission, the French Senate, the UK Foresight Committee, etc. He chairs the Index Advisory Group of Euronext, is a member of the Scientific Committee of the French regulator (AMF), and has been part of the Consultative Workgroup on Financial Innovation of the European Authority (ESMA). Moreover, Charles-Albert received the 2016 Best Paper Award in Finance from Europlace Institute for Finance (EIF) and published more than fifty academic papers and book chapters. He co-authored the book "Market Microstructure in Practice" (World Scientific Publisher, 2nd ed 2018), analyzing the main features of modern markets. He is chairing the “Finance and Insurance Reloaded” transverse research program of the Louis Bachelier Institute; this program explores the influence of new technologies (from blockchain to artificial intelligence) on our industries. "Lightning Talk" Info: CFEM alumna Silvia Ruiz will discuss her team capstone project, which was titled, “How to Predict Stock Movements Using NLP Techniques.” By utilizing NLP techniques, the Cornell CFEM team, sponsored by Rebellion Research, explored whether investing signals can be extracted financial data. The team analyzed 10K and 10Q reports from S&P500 companies using techniques such as FinBERT and word2vec. Silvia Ruiz (MFE Cornell ’20, BS Mathematics Universidad Del Valle ’17) has experience working as a Data Scientist for Corporación Multi Inversiones and as a Risk Analytics Analyst for Morgan Stanley. Dial-In Information: You will receive instructions upon registration.