As an example, in a finance context, folks with certain trading strategies might be interested to predict "whether the general trend of a stock price, during the next 90 days is going to demonstrate a large move in either direction." Further, they may use an error measure that more heavily weights errors in some contexts (say, non-volatile markets).
This is a kind of prediction, carried out in practice by many people. It possibly can be shown equivalent, under some conditions, to some kind of lossy compression -- but such a demonstration of equivalence doesn't seem very straightforward, and the conditions may end up being too weird for the equivalence to be useful or interesting... -- Ben On Wed, Sep 5, 2012 at 7:02 AM, Tim Tyler <[email protected]> wrote: > On 04/09/2012 19:26, Ben Goertzel wrote: > > I guess this is the sort of thing Russell means by the disconnect between > theory and engineering/science practice, regarding the connection between > compression and prediction. > > > I list "latency" and "buffering" as differences on my page about the topic: > > http://matchingpennies.com/forecasting_as_compression/ > > Which is not to deny the mathematical equivalence between prediction > and stream compression - just to say that practical predictors typically > draw from a somewhat different region of the parameter space from > practical stream compressors. > -- > __________ > |im |yler http://timtyler.org/ [email protected] Remove lock to reply. > > *AGI* | Archives <https://www.listbox.com/member/archive/303/=now> > <https://www.listbox.com/member/archive/rss/303/212726-11ac2389> | > Modify<https://www.listbox.com/member/?&;>Your Subscription > <http://www.listbox.com> > -- Ben Goertzel, PhD http://goertzel.org "My humanity is a constant self-overcoming" -- Friedrich Nietzsche ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-c97d2393 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-2484a968 Powered by Listbox: http://www.listbox.com
