Newsletter

Fall 2020

Message from Section Chair

Dear Colleagues and Friends, 

This year has been particularly challenging, as COVID 19 has impacted our lives in important ways. Despite the difficult circumstances, the INFORMS Finance Section has been active throughout the year and engaged in a number of initiatives.

First, I would like you to reserve the date for the 2020 INFORMS Annual Meeting, which will run November 8-12. This is an unusual year, and it will be the first year the Meeting is held virtually. The Finance Section has organized a cluster at the meeting, featuring the wide variety of topics being researched by the Financial Engineering community, including but not limited to Blockchain, Fintech, systemic risk, liquidity risk, etc...  Second, we want to inform you that we have established an advisory board for the INFORMS Finance Section. The board is composed by distinguished practitioners whose research is highly relevant to financial practices, and who will advise on a number of initiatives and matters related to financial analytics and its impact on industry practices. Third, we have initiated a new practitioners best paper award to recognize excellent research done in collaboration with practitioners, and with strong impact on the financial services industry.

I trust we will all go through safely during these rather challenging times, and look forward to seeing you all at the Virtual meeting. And, I am hopeful we will see each other in person soon next year.

Agostino Capponi

President of the INFORMS Finance Section.

The INFORMS Finance Officers, Agostino Capponi (president), Wendy Swenson-Roth (vice-president), Zachary Feinstein (Treasurer), and Daniel Mitchell (Board member), have introduced an advisory board for the section.

The Advisory Board consists of four leaders in the field of Financial Services, Analytics, and Technology industry, who will provide advice on the development of the INFORMS Finance Section.  Serving on the advisory board is a recognition of the individual’s leadership and accomplishments in the field.  The board will overview the operation of the Section, provide advice on various activities, and support Section officers to run the Section effectively and efficiently. 

Nitin Gaur, currently serves as  a Founder and Director of  IBM WW Digital Asset  Labs - serving to device industry standards, use cases and working towards making blockchain for enterprise a reality. Nitin is also a acting CTO of IBM World Wire - a cross border payment solution utilizing digital assets. Nitin also  Founded IBM Blockchain Labs and led the effort in establishing blockchain practice for the enterprise. Prior to this role he was working in capacity of CTO, IBM Mobile Payments and Enterprise Mobile Solutions. Nitin  lead the Application Infrastructure Portfolio of IBM Middleware before taking on MobileFirst Solution portfolio. In his 20 years with IBM he has achieved various industry-recognized certifications. As a technical leader Nitin has been involved in many enterprise project implementations and technical paper presentations  at internal and external conferences . The range of the topics presented by him span from software architectures to improvement of management processes. Nitin, has been focused on staying close to customer  and providing IBM clients with Solution to realize Enterprise Digital Strategy.
Nitin holds MS in Management Information systems and MBA in Finance from University of Maryland. Nitin is also appointed as an IBM Distinguished Engineer and is an IBM Master Inventor with a rich patent portfolio.

Reza Ghanadan is a senior manager at Google AI and the head of public sector AI R&D. He has initiated and led several cross disciplinary programs in AI research and its applications to finance, machine perception, healthcare, e-commerce, education and transportation. Prior to joining Google, Reza served as a program manager at DARPA where he managed 5 large-scale 120M+ multidisciplinary R&D programs in AI, autonomy, data science and a range of real-world applications, for which he was awarded the Department of Defense Distinguished Service Medal. He was a Boeing Technical Fellow at Boeing Research and Technology, Engineering Fellow and Director of information processing department at BAE Systems, founding team member of Flarion Technologies (acquired by Qualcomm), and a member of technical staff group leader at AT&T Bell Laboratories. Reza has initiated and led a number of high profile R&D programs in AI and Autonomy where his work has been featured in several media (e.g. the Washington Post, NBC News, Science, Analytics India). Reza received his Ph.D. in Electrical Engineering from University of Maryland College Park. He also holds an Executive MBA from NYU, M.S. in EE, and two B.S. degrees in EE and in Physics (both Summa Cum Laude).

Gideon Mann is the head of Data Science in the Office of the CTO at Bloomberg LP. At Bloomberg, he guides corporate strategy for machine learning, natural language processing (NLP) and information retrieval. He has over 30 publications and more than 20 patents in machine learning and NLP. He’s served as a founding member of both the Data for Good Exchange (D4GX), an annual conference on data science applications for social good, and the Shift Commission on Work, Workers and Technology. Before joining Bloomberg in 2014, he worked at Google Research NY, where his team carried out basic research, as well as developing machine learning products such as Colaboratory. He holds a Ph.D. from The Johns Hopkins University.

Spyros Schismenos is an Executive Director in the Quantitative Research team at JPMorgan, focusing on mathematical modelling and computational techniques for Counterparty Credit Risk. He has been with JPMorgan since graduating from Cornell University with a PhD in Operations Research in 2009. Spyros is not a stranger to INFORMS, having attended Annual Meetings in the past, as well as being a Nicholson Competition finalist.

Mark S. Squillante is a Distinguished Research Staff Member and the Manager of Foundations of Probability, Dynamics and Control within Mathematical Sciences at the IBM Thomas J. Watson Research Center (Yorktown Heights, NY). He has been an adjunct faculty member in the School of Operations Research and Information Engineering at Cornell Tech (New York, NY) and the School of Engineering and Applied Science at Columbia University (New York, NY), and a Member of the Technical Staff at Bell Telephone Laboratories (Murray Hill, NJ). He received a Ph.D. degree from the University of Washington (Seattle, WA). Mark is an elected Fellow of ACM, IEEE and INFORMS, and his research contributions have been recognized through The Daniel H. Wagner Prize (INFORMS), 9 best paper awards, 17 keynote/plenary presentations, 23 major IBM technical awards, and 31 IBM invention awards. He currently serves as Editor-in-Chief of Stochastic Models and serves on the editorial/advisory board of ACM ToMPECS and Performance Evaluation. His research interests broadly concern mathematical foundations of the analysis, modeling and optimization of the design and control of complex systems under uncertainty.

Below, we list titles and abstracts of papers, which are finalists for this year INFORMS Finance Student Paper context.

Title:  A Reinforcement-Learning Approach to Credit Collections
Authors: Michael Mark, Naveed Chehrazi, and Thomas A. Weber
Abstract: This paper develops a dynamic reinforcement-learning agent capable of finding high-quality policies for the practice of debt collections. At its core, the agent effectively learns how to control a stochastic self-exciting point process in order to maximize an asynchronously obtained reward. Because we use the general formulation of the problem as an agent-environment interaction our results are readily extensible beyond the presented application. Furthermore, with the growing need for interpretable machine-learning models we provide a policy regularization technique which makes learned policies intuitively understandable for human decision makers. Finally, our implementation features a novel “guided exploration” mechanism which improves agent's performance in hard-to-reach states.

Title: Which Factors with Price-Impact Costs?
Authors: Sicong (Allen) Li, Victor DeMiguel, and Alberto Martin-Utrera
Abstract: We show that the squared Sharpe ratio criterion considered by Barillas and Shanken (2017) is no longer appropriate to compare factor models in the presence of price-impact costs. Instead, we propose comparing factor models in terms of their mean-variance utility net of price-impact costs and develop a formal statistical test to compare nested and non-nested factor models. Empirically, we find that price-impact costs change the relative performance of factor models. For instance, while in the absence of costs a seven-factor model considered in DeMiguel, Martin-Utrera, Nogales, and Uppal (2020) is the best low-dimensional model we consider, in the presence of price-impact costs the six-factor model of Fama and French (2018) is better.

Title: Extreme yet Plausible: Choosing Scenarios to Stress Test Financial Institutions
Authors:  Rohit Arora, Rui Gao, and Stathis Tompaidis
Abstract: Since the 2008 Financial Crisis, stress tests based on extreme yet plausible scenarios have become a preferred method of assessing risk for large financial institutions. Yet, scenario choice has largely been ad hoc. We propose a principled methodology to choose scenarios by minimizing the estimation error of the risk of the profit-and-loss (P&L) distribution of a financial institution. We consider two separate cases: 1) a parametric case, when the factors that drive the P&L are assumed to be elliptically distributed; and 2) a non-parametric distributionally robust case, where the underlying distribution of factors is assumed to lie within a distributional uncertainty set based on the Wasserstein metric. Our methodology connects stress testing with the area of Design of Experiments with a risk-based design objective. We illustrate our framework by comparing the accuracy of CVaR achieved with stress scenarios chosen under our framework and stress scenarios chosen in 2019 by the Commodities, Futures, and Trading Commission to stress test Central Counterparties.

Annual Meeting Schedule Overview

This year the INFORMS Annual Meeting will be held virtually.  Though the talks will be pre-recorded, each session of the conference will be followed directly by Live Q&A sessions.  We hope you all join for the same spirited discussions following the talks as in prior years.  The Finance Section is hosting 14 sessions this year including the session for the Student Paper Award Finalists.  All sessions will take place in the afternoon (Eastern Time) and continue throughout the conference from Sunday, November 8 through Thursday, November 12.  In addition to our usual focus on financial engineering and financial mathematical problems related to pricing, risk, and portfolio selection, this year we are hosting numerous sessions focused on machine learning in finance and financial technology.  A general overview of the schedule is as follows:

Please note that the Business Meeting will be held on Monday, November 9 at 5:45-6:45PM Eastern Time through Zoom.  The Business Meeting can be accessed directly by following the link: https://zoom.us/j/99133823964?pwd=VGtHVHpYczlXZzJNU0NEVmVJdlF1Zz09 or by using the Meeting ID: 991 3382 3964 and Password: 5521.

Please note that the Business Meeting will be held on Monday, November 9 at 5:45-6:45PM Eastern Time through Zoom.  The Business Meeting can be accessed directly by following the link: https://zoom.us/j/99133823964?pwd=VGtHVHpYczlXZzJNU0NEVmVJdlF1Zz09 or by using the Meeting ID: 991 3382 3964 and Password: 5521.

Agostino Capponi               Chair                                ac3827@columbia.edu
Wendy Swenson-Roth       Vice-Chair                       wroth@gsu.edu
Zachary Feinstein              Secretary/Treasurer         zfeinste@stevens.edu
Daniel Mitchell                    Board member                 damitche@umn.edu