Andrew Ang (Columbia University, Graduate School of Business)
Title: Private Equity Returns
We discuss the creation of a new, more accurate returns-based index for private equity and other illiquid asset classes.
Rick Bookstaber (Office of Financial Research)
Title: Agent-based Models and Risk Management Version 3.0
Portfolio Value-at-risk and related risk metrics rely on history, and do well if the future is drawn from the same distribution as the past. This means they work almost all of the time -- but not when it really matters. Stress testing has been the recent response to this limitation in VaR methodologies. Stress tests can posit a shock that has no recent historical precedent, but stress testing still fails to hit the mark, because it gives a static view of the implications of a shock. What is missing from stress tests is the answer to the question, "and then what happens?". Agent based models are an approach that moves risk management to the next stage, allowing us to follow the feedback and dynamics as the shocks propagate throughout the financial system.
Peter Carr (Morgan Stanley)
Title: Risk, Return and Ross Recovery
Recently, Stephen Ross has shown that the real-world transition probabilities of a finite state Markov chain can be recovered from Arrow Debreu security prices by assuming that the pricing kernel enjoys transition independence. We motivate this restriction by deriving it as a consequence of restricting the form and dynamics of the numeraire portfolio. Working with a diffusion process for a short interest rate, we indicate how one can recover real world transition probabilities on both bounded and unbounded domains.
David Easley (Cornell University)
Title: Optimal Execution Horizon
Execution traders know that market impact greatly depends on whether their orders lean with or against the market. We introduce the OEH model, which incorporates this fact when determining the optimal trading horizon for an order, an input required by many sophisticated execution strategies. From a theoretical perspective, OEH explains why market participants may rationally “dump” their orders in an increasingly illiquid market. OEH is shown to perform better than participation rate schemes and VWAP strategies. We argue that trade side and order imbalance are key variables needed for modeling market impact functions, and their dismissal may be the reason behind the apparent disagreement in the literature regarding the functional form of the market impact function. Our backtests suggest that OEH contributes substantial 'execution alpha' for a wide variety of futures contracts. An implementation of OEH is provided in Python language. (Joint work with Marcos Lopez de Prado and Maureen O' Hara)
Gary Kazantsev (Bloomberg Research)
Title: Machine Learning in Finance
The talk will give an overview of the evolution and challenges of machine learning and 'big data' in finance from the perspective of development of analytical products. More precisely, we will discuss several current applications of machine learning in finance from a practical engineering point of view and provide some insight into the trajectory of 'big data' in the financial industry.
Michael Kearns (University of Pennsylvania)
Title: Machine Learning for Market Microstructure
Through a series of brief case studies, I will highlight both the promise and challenge of applying modern machine learning methods to trading problems arising from market microstructure data.
Muthu Muthukrishnan (Rutgers University and Microsoft Research)
Title: Online Ad Markets
We discuss three aspects of online ad markets: (i) In sponsored search, how can we reason about the market structure? (ii) In display ads and ad exchanges, what are real time decision problems and suitable algorithms? (iii) In social advertising, what are suitable ad markets and associated design issues? The technical challenges in answering these questions involve issues in the interface of Economics, Computer Science, and methods of Financial Engineering.
Vinay Nair (ADA Investments)
Title: Emerging Markets
We plan to highlight some of the current challenges in this asset class and highlight the more general problem of unintended exposures using this market as an example.