Faculty Candidate: Rina Panigrahy
480 Dreese Labs
2015 Neil Avenue
Columbus, Ohio 43210
Prediction Strategies without Loss
Is it possible to invest in the stock market in a way that you never lose money and gain when the stock market goes up a lot (won't that be nice)?
We will show that at least in an extreme theoretical sense this may not be entirely impossible. Under some idealized assumptions we show that there is an investment strategy that doesn't lose beyond a negligible (exponentially small) amount if the market falls and gains at least some if the market has high gains. The assumption we make is that the per day change in stock price is bounded -- say at most 1%. Under more realistic assumptions this work shows how to obtain the optimal trade-off between risk and reward in an investment strategy.
We will also look at how these algorithms do in practice.
Rina Panigrahy is a Research Scientist at Google. Before this he was a principal researcher at Microsoft Research specializing in theoretical and applied algorithms in areas such as high dimensional search, hashing, sketching, streaming, graph analysis, learning and prediction. He has a masters from MIT and a Ph.D. from Stanford. His work at MIT was used in founding Akamai Technologies. Before his PhD he spent 8 years as an engineer at Cisco Systems. He is a recipient of a gold medal at the International Math Olympiad and a winner a couple of best paper awards.