Re: Any way to tell what features contributed the most for a particular decision?

Dang the bloody mail delays. Chris was much faster 'n me.

Take his advice to the letter, mix 'n mash with what I said, and make
darn sure you never ever sell a /guarantee/ on this stuff. **
Statistics/probabilistics and guarantees don't go together. ** The
operative word is /quite/. As in: "it works quite well." If you like
your stakes done high, you might try "very" instead of "quite", but
before you do, just go and ask the actuarian wizzards (no spelling
error, cf. Pratchett) on Wall Street, Paris or wherever how they feel
right now about their previously "very safe" statistics-based
operations before you take that word in your mouth.

Bill may be ranking in the TOP10 at TREC but that doesn't mean you can
quote his numbers (or anybody else's) there for your game. People have
been burned that way before.

Just a friendly general warning up front.


-- 
Met vriendelijke groeten / Best regards,

Ger Hobbelt

--------------------------------------------------
web:    http://www.hobbelt.com/
        http://www.hebbut.net/
mail:   [email protected]
mobile: +31-6-11 120 978
--------------------------------------------------

-------------------------------------------------------------------------
This SF.Net email is sponsored by the Moblin Your Move Developer's challenge
Build the coolest Linux based applications with Moblin SDK & win great prizes
Grand prize is a trip for two to an Open Source event anywhere in the world
http://moblin-contest.org/redirect.php?banner_id=100&url=/