Prediction Strategies without Loss

Add to your list(s) Download to your calendar using vCal

• Rina Panigrahy, Senior Researcher, MSR-Silicon Valley Campus
• Friday 13 July 2012, 11:00-12:00
• Large public lecture room, Microsoft Research Ltd, 7 J J Thomson Avenue (Off Madingley Road), Cambridge.

If you have a question about this talk, please contact Microsoft Research Cambridge Talks Admins.

This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending

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? (wont that be nice.)

We show that this may not be entirely impossible. In fact it is pretty much possible at least in a theoretical sense. Under some simplifying assumptions we show that there is an investment strategy that doesn’t lose much if the market falls and gains some if the market gains while giving up some of the gains. The assumption we make is that the per day change is bounded say at most 1%. While the 1% bound may not be always true in practice it is indeed not more than a few multiples in most days.

We will also look at how these algorithms do in practice. http://arxiv4.library.cornell.edu/abs/1008.3672 (NIPS 2012)

This talk is part of the Microsoft Research Machine Learning and Perception Seminars series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge talks
• Chris Davis' list
• Guy Emerson's list
• Interested Talks
• Large public lecture room, Microsoft Research Ltd, 7 J J Thomson Avenue (Off Madingley Road), Cambridge
• ML
• Machine Learning Summary
• Microsoft Research Cambridge, public talks
• Microsoft Research Machine Learning and Perception Seminars
• Optics for the Cloud
• PMRFPS's
• School of Technology
• Trust & Technology Initiative - interesting events
• bld31
• ndk22's list
• ob366-ai4er
• personal list
• rp587
• yk373's list

Note that ex-directory lists are not shown.