[mythtv] Bayesian analysis

[Kirby Vandivort]

On Sat, Nov 15, 2003 at 02:43:34PM +0000, Steve Hill wrote:
> 
> I've been working on a bayesian analysis system to try and identify 
> programs that might be interesting.
> 
> If anyone's interested, my initial efforts are online at:
> 	http://www.nexusuk.org/projects/mythbayes/
> 
> I'm not sure how good it'll be - mine has only just started learning.  It 
> picks out the shows that are already being recorded very well (which of 
> course isn't so useful :).  It does seem to catch some interesting stuff 
> that's not being recorded already, and I'm hoping it'll improve as it 
> learns.  Any feedback is appreciated.
> 

Well, mine give me 500 programs that its not recording that I've never
heard of.  :)

At any rate, we need to get together on this.  I'm currently in the
process of writing some code that will add rankings to the user interface
where users can rate random programs that they like or dislike and the
step i was planning after that was to do the bayesian.  (perhaps you've
looked at the recommendations patches that I sent to the list a couple
of months ago.  If not, I would recommend trying it out)


http://www.gossamer-threads.com/perl/mailarc/gforum.cgi?guest=1571452&t=search_engine&do%3Dpost_view_flat%3Bsb%3Dpost_latest_reply%3Bso%3DASC%3Bpost%3D81943=View+Flat+Mode#81943


-- 

Kirby Vandivort                      Theoretical and 
Senior Research Programmer            Computational Biophysics 
Email: kvandivo at ks.uiuc.edu          3051 Beckman Institute
http://www.ks.uiuc.edu/~kvandivo/    University of Illinois
Phone: (217) 244-5711                405 N. Mathews Ave
Fax  : (217) 244-6078                Urbana, IL  61801, USA