Join us for the Brooklyn Quant Experience (BQE) Lecture Series today,  Thursday, May 5th at 6 pm ET on Zoom.

“Simulacrum or Shenanigan: Deep Generative Models and Simulators for Financial Markets”

Derek Snow
Visiting Industry Assistant Professor
Department of Finance and Risk Engineering 
NYU Tandon

Attend Virtually >>

*Please note a meeting password is required for this event.
Meeting ID: 995 3136 9451
Password: BQEDS55

Abstract

Deep generative models are synthetic data generators that use deep learning algorithms to generate data that preserves the original data’s statistical features while producing entirely new data points. Deep generative models are not dynamic or reactive, whereas other data-generating techniques like multi-agent market simulators are. This presentation will identify the differences between these methods and discuss a new third-way approach that combines deep learning and agent-based models.

Bio

Derek is an assistant professor at NYU and an associate member at Oxford University’s Man Institute of Quantitative Finance and The Alan Turing Institute, the UK’s national institute for Artificial Intelligence. He was previously a visiting Doctoral scholar at the University of Cambridge and NYU’s School of Engineering. He received his Ph.D. and Honours degree with distinction from the University of Auckland, studying topics in Machine Learning for Finance. Derek has worked with some of the world’s largest quantitative research firms, and his software receives thousands of monthly downloads.

Featuring Machine Learning experts from Cornell, Citi, and more…

You and your colleagues are invited to attend the Cornell Financial Data Science Webinars. Through online talks in Spring 2022, we are excited to collaborate with various guest speakers in highlighting machine learning applications in finance.

All webinars are from 5:00 pm to 6:00 pm ET.

This webinar is free and open to all guests. Registration is required (please RSVP here). You will receive the webinar link and dial-in info upon registration (the confirmation email will come from no-reply@zoom.us).

Abstract: 

Orders in major electronic stock markets are executed through centralised limit order books (LOBs). The availability of historical data have led to extensive research modelling LOBs. Better understanding the dynamics of LOBs and building simulators as a framework for controlled experiments, when testing trading algorithms or execution strategies are among the aims in this area. Most work in the literature models the aggregate view of the limit order book, which focuses on the volume of orders at a given price level using a point process. In addition to this aggregate view, brokers and exchanges also have information on the identity of the agents submitting the order to them. This leads to a more complicated representation of limit order book dynamics, which we attempt to model using a heterogeneous model of order flow.

We present a granular representation of the limit order book, that allows to account for the origins of different orders. Using client order flow from a large broker, we analyze the properties of variables in this representation. The heterogeneity of the order flow is modeled by segmenting clients into different clusters, for which we identify representative prototypes. This segmentation appears to be stable both over time, as well as over different stocks. Our findings can be leveraged to build more realistic order flow models that account for the diversity of market participants.

Speaker Bio:

Felix Prenzel is a Ph.D. student part of the Centre of Doctoral Training in Mathematics of Random Systems at the University of Oxford. He is supervised by Prof. Rama Cont and Prof. Mihai Cucuringu. His research primarily concerns data-driven modeling of limit order books with the aim to build realistic training environments for trading applications.

We hope to see you online!

**Please excuse any duplication of this announcement

If you are interested in our past seminars, you are welcome to subscribe to our YouTube Channel and watch our videos!

Past Events

February 15, 2022
Speaker: Kevin Webster
Title of Presentation: “How Price Impact Distorts Accounting P&L – Revisiting Caccioli, Bouchaud and Farmer’s Impact-Adjusted Valuation”

March 22, 2022
Speaker: Maarten Scholl (Oxford)
Title of Presentation: “Studying Market Ecology Using Agent-Based Models”

April 26, 2022
Speaker: Andreea Minca (Cornell ORIE)
Title of Presentation: “Clustering Heterogeneous Financial Networks”