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: 

This talk presents a mathematical analogy between financial trading strategies and biological species and shows how to apply standard concepts from ecology to financial markets. We analyze the interactions of stereotypical trading strategies in ecological terms, showing that they can be competitive, predator-prey, or mutualistic, depending on the wealth invested in each strategy. The deterministic dynamics suggest that the system should evolve toward an efficient state where all strategies make the same average returns. However, this happens slowly, and the evolution is so noisy that there are large fluctuations away from the efficient state, causing bursts of volatility and extended periods where prices deviate from fundamental values.

Speaker Bio:

Maarten P. Scholl is a PhD student at the Institute for New Economic Thinking (INET) at the Oxford Martin School and the Department of Computer Science. He works on classifying financial market activities using regulatory reporting data and uses Agent-Based Models (ABMs) to simulate financial market scenarios to uncover all possible interactions between market activities.

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”

Upcoming Events

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

It is with indescribable sadness that we write to inform you that Professor Peter Carr passed away last week. Peter touched so many lives in the FRE Department, NYU Tandon community, and within the finance industry.

Our BQE Lecture Series was created by Peter when he joined the department in 2016. We will keep his legacy alive and continue sharing events and research by other practitioners in financial engineering.

We hope you can join us.

Join us for the Brooklyn Quant Experience (BQE) Lecture Series on Thursday, March 10th at 6 pm ET on Zoom.

“Optimal Execution with Quadratic Variation Inventories”

Laura Leal
Ph.D. Student
Operations Research and Financial Engineering Department
Princeton University

Attend Virtually >>

*Please note a meeting password is required for this event.
Meeting ID: 922 7756 8804
Password: BQELL310

Abstract

We describe and implement statistical tests arguing for the presence of a Brownian component in the inventories and wealth processes of individual traders. Using intra-day data from the Toronto Stock Exchange, we provide empirical evidence of this claim. Both for regularly spaced time intervals, as well as for asynchronously observed data, the tests reveal with high significance the presence of a non-zero Brownian motion component. Furthermore, we extend the theoretical analysis of an existing optimal execution model to accommodate the presence of Ito inventory processes, and we compare empirically the optimal behavior of traders in such fitted models, to the actual behavior read off the data.

Bio
Laura Leal is a final-year Ph.D. student in the Operations Research and Financial Engineering department at Princeton University. Her research interests are centered in high-frequency finance, using machine learning, deep neural networks, optimization, statistical and econometric methods to study high-frequency trading data. The main topics she has worked on include optimal execution, market making, identification of institutional activity, and tail risk.

Join us for the Brooklyn Quant Experience (BQE) Lecture Series on Thursday, February 24th at 6 pm ET on Zoom.

“Dependent Stopping Times and an Application to Credit Risk Theory”

Alejandra Quintos Lima
Ph.D. Candidate in Statistics
Columbia University

Attend Virtually >>

*Please note a meeting password is required for this event.
Meeting ID: 983 0682 8534
Password: BQEAQL224

Abstract

Stopping times are used in applications to model random arrivals. A standard assumption in many models is that the stopping times are conditionally independent, given an underlying filtration. This is a widely useful assumption, but there are circumstances where it seems to be unnecessarily strong. In the first part of the talk, we use a modified Cox construction, along with the bivariate exponential introduced by Marshall & Olkin (1967), to create a family of stopping times, which are not necessarily conditionally independent, allowing for a positive probability for them to be equal. We also present a series of results exploring the special properties of this construction.

In the second part of the talk, we present an application of our model to Credit Risk. We characterize the probability of a market failure which is defined as the default of two or more globally systemically important banks (G-SIBs) in a small interval of time. The default probabilities of the G-SIBs are correlated through the possible existence of a market-wide stress event. We derive various theorems related to market failure probabilities, such as the probability of a catastrophic market failure, the impact of increasing the number of G-SIBs in an economy, and the impact of changing the initial conditions of the economy’s state variables. We also show that if there are too many G-SIBs, a market failure is inevitable, i.e., the probability of a market failure tends to one as the number of G-SIBs tends to infinity.

Bio
Alejandra is finishing her Ph.D. in Statistics at Columbia University under the direction of Prof. Philip Protter. Her research interests lie primarily in problems in probability, stochastic processes, and statistics motivated by their applications, particularly those applications in mathematical finance. During her Ph.D. program, Alejandra held a Fulbright grant, and she was one of the finalists for the 2021 Presidential Awards for Outstanding Teaching by a Graduate Student at Columbia University. Before graduate school, she worked for Citigroup in Mexico, participated in a summer research program at Cornell University, and did an internship in DC. She held a merit scholarship to major in Actuarial Sciences in UDLAP (Puebla, Mexico) where she graduated as Summa Cum Laude and was the Valedictorian of her class.

Join us for the Brooklyn Quant Experience (BQE) Lecture Series on Thursday, February 17th at 6 pm ET on Zoom.

“James-Stein Estimation of Minimum Variance Portfolios”

Alex Shkolnik
Assistant Professor
University of California Santa Barbara

Attend Virtually >>

*Please note a meeting password is required for this event.
Meeting ID: 984 1537 6549
Password: BQEAS217

Abstract
In quantitative finance, estimated covariance matrices are routinely used to construct portfolios with mean-variance optimization. It is widely recognized, however, that the embedded sampling error tricks the optimizer into constructing distorted and highly inefficient portfolios. This problem is further amplified when the number of securities vastly exceeds the number of observations. We quantify this inefficiency with a metric we call the optimization bias which depends primarily on the leading eigenvector of a sample covariance matrix. Under a spiked covariance model, we prove that the optimization bias may be completely erased given just two observations of the security return but provided that the number of securities tends to infinity. We illustrate the theory with numerical simulations that provide further insight into the behavior of the proposed estimator in practice. We conclude the talk by establishing rich connections between the Stein paradox in statistics, the beta adjustments commonly used in the financial industry, and the James-Stein estimator of a principal component.

Bio
Alex Shkolnik is an Assistant Professor at the Department of Statistics and Applied Probability at the University of California, Santa Barbara, and a Research Fellow at the Consortium for Data Analytics in Risk at the University of California, Berkeley where he was a postdoctoral scholar. Alex received his Ph.D. in computational mathematics and engineering from Stanford University in 2015. His research interests include Monte Carlo simulation, high-dimensional statistics, and quantitative financial risk management.

The Brooklyn Quant Experience (BQE) Lecture Series returns for the Spring 2022 semester on Thursday, February 10th at 6 pm ET on Zoom.

A Gentle Introduction to Adjoint Algorithmic Differentiation (AAD):
(How to Better Hedge Financial Risk, Crack Some Puzzles of Condensed Matters and Much More with Upside-Down Derivatives)

Luca Capriotti
Global Head of Quantitative Strategies
Credit Suisse

Attend Virtually >>

*Please note a meeting password is required for this event.
Meeting ID: 998 1185 8126
Password: BQELC210

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: 

This presentation revisits the key message from Caccioli, Bouchaud, and Farmer (2012) “A proposal for impact-adjusted valuation”: traditional marked to mid accounting P&L overestimates a portfolio’s true P&L.

Under the Obhizaeva and Wang model, this talk proves that marked to mid P&L is mechanically inflated by price impact. This artificial P&L never persists. It either slowly deflates over time or evaporates during liquidation.

As pointed out by Caccioli, Bouchaud, and Farmer, applications of these results include portfolio and risk management, extending the reach of price impact models outside of traditional trading problems.

Speaker Bio:

Dr. Kevin Webster graduated with a Ph.D. from Princeton University Operations Research and Financial Engineering Department (ORFE). At ORFE, he studied mathematical models applied to high-frequency trading, with a large emphasis on price impact and market-making.

Upon graduation in 2014, he worked initially as a researcher at Deutsche Bank and then joined Citadel in 2016. He is currently on garden leave from Citadel.

Dr. Kevin Webster created and taught a course, ORF 474 High-Frequency Markets: Models and Data Analysis, as a visiting lecturer at Princeton in the 2015 school year. His publications include “The self-financing equation in high-frequency markets,” “Information and inventories in high-frequency trading,” “A portfolio manager’s guidebook to trade execution,” and “High-frequency market-making.”

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!

Upcoming Events

April 2022
Speaker: Andreea Minca (Cornell)
Title of Presentation: TBD

Join us for last the Brooklyn Quant Experience (BQE) Lecture Series for the Fall 2021 semester on Thursday, December 9th at 6 pm ET on Zoom. Only NYU students, faculty, and staff are allowed to attend in person. All other guests can attend synchronously via Zoom.

“Tradable Carbon Permits Auctions Under Regulation and Competition”

Bruno Kamdem
Co-founder and Principal
Lepton Actuarial & Consulting, LLC
and
Adjunct Professor
NYU Tandon FRE

Attend Virtually >>

*Please note a meeting password is required for this event.
Meeting ID: 955 1090 2494
Password: BQEBM129

Join us for the Brooklyn Quant Experience (BQE) Lecture Series on Thursday, December 2nd at 6 pm ET on Zoom. Only NYU students, faculty, and staff are allowed to attend in person. All other guests can attend synchronously via Zoom.

“Machine Learning in Financial Services”

Frederic Siboulet
Adjunct Professor
NYU Tandon FRE

Attend Virtually >>

*Please note a meeting password is required for this event.
Meeting ID: 981 8403 9166
Password: BQEFS122

Join us for the Brooklyn Quant Experience (BQE) Lecture Series on Thursday, November 18th at 6 pm ET on Zoom. Only NYU students, faculty, and staff are allowed to attend in person. All other guests can attend synchronously via Zoom.

“Market Liquidity Risk in Financial Markets”

Naresh Malhotra
Director/Supervisor
Societe Generale

Attend Virtually >>

*Please note a meeting password is required for this event.
Meeting ID: 910 3757 1986
Password: BQENM1118

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

You and your colleagues are invited to attend the Cornell – Citi Financial Data Science Webinars. Through online talks in Fall 2021, we are excited to collaborate with Citi in highlighting machine learning applications in finance. Our upcoming talk builds on the neural network modeling topic discussed in the seminar with Zihao Zhang (Oxford-Man Institute), which you can watch online.

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:  We use a deep neural network to generate controllers for optimal trading on high-frequency data. For the first time, a neural network learns the mapping between the preferences of the trader, i.e. risk aversion parameters, and the optimal controls. An important challenge in learning this mapping is that, in intra-day trading, traders’ actions influence price dynamics in closed-loop via the market impact. The issue of scarcity of financial data is solved by transfer learning: the neural network is first trained on trajectories generated thanks to a Monte-Carlo scheme, leading to a good initialization before training on historical trajectories. Moreover, to answer genuine requests of financial regulators on the explainability of machine learning generated controls, we project the obtained “blackbox controls” on the space usually spanned by the closed-form solution of the stylized optimal trading problem, leading to a transparent structure. For more realistic loss functions that have no closed-form solution, we show that the average distance between the generated controls and their explainable version remains small. This opens the door to the acceptance of ML-generated controls by financial regulators.

Speaker Bio: Laura Leal is a final-year Ph.D. student in the Operations Research and Financial Engineering department at Princeton University. Her research interests are centered in high-frequency finance, using machine learning, deep neural networks, optimization, statistical and econometric methods to study high-frequency trading data. The main topics she has worked on include optimal execution, market making, identification of institutional activity, and tail risk.

We hope to see you online!

The Cornell-Citi Team

**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

Oct. 1-3, 2021
5th Eastern Conference on Mathematical Finance (ECMF)

Oct. 5^th, 2021
Speaker: Alok Dutt (Citigroup)
Title of Presentation: The Top Challenges for a Financial Data Scientist (And How to Overcome Them)

Oct. 26th, 2021
Speaker: Zihao Zhang
Title of Presentation: Deep Learning for Market by Order Data