2018年12月19日（周三） 10:00-11:30 a.m.
We consider the problem of algorithmic bidding in repeated auctions of goods with random clearing prices and payoffs. This problem arises naturally in electricity markets where market participants arbitrage electricity across time or locations. Online advertising is another example where advertisers bid to buy ad spaces online, not knowing the payoffs of such ads buys. In both cases, the price and the value of the goods can be modeled as random variables with unknown joint distributions. A bidder needs to choose what goods to bid and their bidding prices subject to budget constraints. A bidder can be risk neutral or risk averse.
In this talk, we present an online learning approach to algorithmic bidding in repeated auctions. Using virtual trading in a two-settlement market as an example, we develop an online learning algorithm that maximizes the cumulative return from the bidding strategy under both risk-neutral and risk-averse performance measures. It is shown that the expected payoff of the proposed algorithm converges, with an almost optimal convergence rate, to the expected payoff of the global optimal policy corresponding to the case when the underlying price distribution is known. We demonstrate that the proposed strategy outperforms existing machine learning benchmarks and achieves significant profit consistently based on historical data from the NYISO and PJM markets over the eleven-year period between 2006 and 2016.
This is a joint work with Sevi Baltaoglu and Qing Zhao.
Lang Tong joined Cornell University in 1998 where he is now the Irwin and Joan Jacobs Professor in Engineering and the Cornell site director of the Power Systems Engineering Research Center (PSerc). He received the B.E. degree from Tsinghua University, Beijing, P.R. China in 1985, and PhD degree in EE from the University of Notre Dame, Notre Dame, Indiana in 1991. He was a Postdoctoral Research Affiliate at the Information Systems Laboratory, Stanford University in 1991.
Lang Tong's current research focuses on energy systems and smart power grid. In particular, his group investigates data analytics, system optimization, and market issues associated with renewable energy, storage, and the electrification of transportation systems. He is part of the Engineering and Economics of Electricity Research Group.
Professor Tong is the 2018 Fulbright Distinguished Chair in Alternative Energy. A Fellow of IEEE and a Distinguished Lecturer (2009), Professor Tong received numerous paper awards including the IEEE Signal Processing Society Best Paper Award (2004), IEEE Communications Society Leonard G. Abraham Prize Paper Award (2004), IEEE Circuits and Systems Society Outstanding Young Author Award (1993), IEEE Power & Energy Systems General Meeting Best Paper Selection (2015,2016,2018). He is a coauthor of seven student paper awards, including two IEEE Signal Processing Society Young Author Best Paper Awards (2000,2008) for papers published in the IEEE Transactions on Signal Processing.