**Subject: **BISC: A challenge to data miners: the soccer problem

**From: **Michelle T. Lin (*michlin@eecs.berkeley.edu*)

**Date: **Tue Jul 18 2000 - 19:57:42 MET DST

**sorted by:**[ date ] [ thread ] [ subject ] [ author ]**Next message:**Michelle T. Lin: "BISC: resend"**Previous message:**Paul Victor Birke: "Re: Problem in Fuzzy Risk Analysis"

*********************************************************************

Berkeley Initiative in Soft Computing (BISC)

*********************************************************************

To: BISC Group

From: L. A. Zadeh <zadeh@cs.berkeley.edu>

A Challenge to Data Miners: The Soccer Problem

----------------------------------------------

Recently, I was watching the soccer match between France and

Portugal. I noticed that most of the time the ball was in the vicinity

of the goal of Portugal. This observation suggested the following

hypothesis, call it H.

For generality, let the opposing sides be labeled A and B. Let

r be the fraction of time the ball spends in the vicinity of the goal

of A. The hypothesis is that the closer the value of r is to 1, the

higher the probability that B will win.

To make the hypothesis more concrete, assume that r is

measured as follows. Let the playing field be partitional into zones

R1,...Rn, with R1 being nearest to the goal of A and Rn the farthest.

Let ri be the fraction of time the ball spends in Ri, i=1,..,n. Let

wi, i=1,..,n be weights ranging in magnitude from 0 to 1. Then

r=w1r1+...+wnrn.

Does there exist a choice of the Ri and this wi such that H is

true? This is the crux of the problem. The assumption is that we

analyze N games, with r computed at the end of each game. The result

for game j, j=1,..,N, will be W(j) (win), D(j) (draw) and L(j) (lose),

with r being r(j), j=1,..,N. These data, then, would serve as a basis

for testing H.

The soccer problem is an instance of a problem in data mining

in which a hypothesis, H, is (a) generated; (b) tested; and (c)

modified. In my view, it is a challenging problem because how to

choose and adjust the Ri and wi is not a simple matter.

Regards to all,

Lotfi

----------------------------------------------------------

Lotfi A. Zadeh

Professor in the Graduate School and Director,

Berkeley Initiative in Soft Computing (BISC)

CS Division, Department of EECS

University of California

Berkeley, CA 94720-1776

Tel/office: (510) 642-4959 Fax/office: (510) 642-1712

Tel/home: (510) 526-2569 Fax/home: (510) 526-2433

email: zadeh@cs.berkeley.edu

http://www.cs.berkeley.edu/People/Faculty/Homepages/zadeh.html

----------------------------------------------------------

To post your comments to the BISC Group, please send them to

Michael Berthold: berthold@cs.berkeley.edu

--------------------------------------------------------------------

If you ever want to remove yourself from this mailing list,

you can send mail to <Majordomo@EECS.Berkeley.EDU> with the following

command in the body of your email message:

unsubscribe bisc-group

or from another account,

unsubscribe bisc-group <your_email_adress>

############################################################################

This message was posted through the fuzzy mailing list.

(1) To subscribe to this mailing list, send a message body of

"SUB FUZZY-MAIL myFirstName mySurname" to listproc@dbai.tuwien.ac.at

(2) To unsubscribe from this mailing list, send a message body of

"UNSUB FUZZY-MAIL" or "UNSUB FUZZY-MAIL yoursubscription@email.address.com"

to listproc@dbai.tuwien.ac.at

(3) To reach the human who maintains the list, send mail to

fuzzy-owner@dbai.tuwien.ac.at

(4) WWW access and other information on Fuzzy Sets and Logic see

http://www.dbai.tuwien.ac.at/ftp/mlowner/fuzzy-mail.info

(5) WWW archive: http://www.dbai.tuwien.ac.at/marchives/fuzzy-mail/index.html

**Next message:**Michelle T. Lin: "BISC: resend"**Previous message:**Paul Victor Birke: "Re: Problem in Fuzzy Risk Analysis"

*
This archive was generated by hypermail 2b25
: Tue Jul 18 2000 - 20:10:51 MET DST
*