 |
|
|
|
|
|
|
|
|
|
|
|
|
 |
|
|||||||||||
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
|
|
 |
 |
|
||||||||||
 |
|
|||||||||||
 |
|
|||||||||||
 |
 |
|
||||||||||
| Seminar Schedule (Seminar Organizer: Prof. Ziv Bar-Joseph) | |
Machine Learning Lunchtime Chats
|
Spring 2007 Seminar
Date: April 27, 2007 Time: 3:00 PM - 4:00 PM Location: 3305 Newell-Simon Hall Speaker: Chris Murray MS Candidate Title: Feature and Expert-based Market Prediction using Online Low-regret Algorithms Abstract: For decades, people have expended untold amount of effort trying to predict the stock market. We frame market prediction an experts problem, in the online learning sense, and show that simple strategies have optimal regret properties. We also show how to take advantage of recent empirical results in finance by creating feature portfolios, and how these can be used to achieve dramatic returns within the low-regret framework.