You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@spamassassin.apache.org by bu...@bugzilla.spamassassin.org on 2005/04/07 22:43:52 UTC

[Bug 4248] New: generate optimized advance fee rules

http://bugzilla.spamassassin.org/show_bug.cgi?id=4248

           Summary: generate optimized advance fee rules
           Product: Spamassassin
           Version: SVN Trunk (Latest Devel Version)
          Platform: Other
        OS/Version: other
            Status: NEW
          Severity: normal
          Priority: P5
         Component: Rules
        AssignedTo: henry@stern.ca
        ReportedBy: quinlan@pathname.com
                CC: dev@spamassassin.apache.org


We have way too many advance fee fraud rules, we need a way to reduce
that number and pick the optimal subset.

Henry is working on this for 3.1.0.



------- You are receiving this mail because: -------
You are on the CC list for the bug, or are watching someone who is.

[Bug 4248] generate optimized advance fee rules

Posted by bu...@bugzilla.spamassassin.org.
http://bugzilla.spamassassin.org/show_bug.cgi?id=4248





------- Additional Comments From henry@stern.ca  2005-04-09 00:45 -------
I ran it on my own (unbiased) corpus.  The spam is two weeks old.

OVERALL%   SPAM%     HAM%     S/O    RANK   SCORE  NAME
   2292     1145     1147    0.500   0.00    0.00  (all messages)
100.000  49.9564  50.0436    0.500   0.00    0.00  (all messages as %)
  1.876   3.7555   0.0000    1.000   1.00    0.01  T_ADVANCE_FEE_3
  1.832   3.6681   0.0000    1.000   0.77    0.01  T_ADVANCE_FEE_4
  2.051   4.0175   0.0872    0.979   0.69    0.01  T_ADVANCE_FEE_2
  1.702   3.4061   0.0000    1.000   0.54    1.40  ADVANCE_FEE_3
  1.920   3.7555   0.0872    0.977   0.46    2.48  ADVANCE_FEE_1
  3.141   5.7642   0.5231    0.917   0.38    0.01  T_ADVANCE_FEE_1
  1.527   3.0568   0.0000    1.000   0.31    1.82  ADVANCE_FEE_4
  1.745   3.4061   0.0872    0.975   0.00    2.40  ADVANCE_FEE_2



------- You are receiving this mail because: -------
You are on the CC list for the bug, or are watching someone who is.

[Bug 4248] generate optimized advance fee rules

Posted by bu...@bugzilla.spamassassin.org.
http://bugzilla.spamassassin.org/show_bug.cgi?id=4248


quinlan@pathname.com changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|ASSIGNED                    |RESOLVED
         Resolution|                            |FIXED




------- Additional Comments From quinlan@pathname.com  2005-04-29 01:18 -------
checked in final rules, commented out inactive predicate rules and moved
them to 70_broken_tests.cf




------- You are receiving this mail because: -------
You are on the CC list for the bug, or are watching someone who is.

[Bug 4248] generate optimized advance fee rules

Posted by bu...@bugzilla.spamassassin.org.
http://bugzilla.spamassassin.org/show_bug.cgi?id=4248


henry@stern.ca changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|NEW                         |ASSIGNED
   Target Milestone|Undefined                   |3.1.0




------- Additional Comments From henry@stern.ca  2005-04-09 03:34 -------
Committed to trunk, revision 160676.

 * masses/evolve_metarule
 * masses/evolve_metarule/evolve_metarule.c
 * masses/evolve_metarule/preproc.pl
 * masses/evolve_metarule/Makefile
 * masses/evolve_metarule/README



------- You are receiving this mail because: -------
You are on the CC list for the bug, or are watching someone who is.

[Bug 4248] generate optimized advance fee rules

Posted by bu...@bugzilla.spamassassin.org.
http://bugzilla.spamassassin.org/show_bug.cgi?id=4248





------- Additional Comments From quinlan@pathname.com  2005-04-08 15:02 -------
Interesting results for the first test... looks like 1 and 2 have too many
false positives, but 3 and 4 are great.

OVERALL%   SPAM%     HAM%     S/O    RANK   SCORE  NAME
 443271   347311    95960    0.784   0.00    0.00  (all messages)
100.000  78.3518  21.6482    0.784   0.00    0.00  (all messages as %)
  1.084   1.3838   0.0010    0.999   0.85    0.01  T_ADVANCE_FEE_3
  1.039   1.3256   0.0021    0.998   0.84    2.40  ADVANCE_FEE_2
  0.937   1.1958   0.0000    1.000   0.82    0.01  T_ADVANCE_FEE_4
  1.145   1.4563   0.0167    0.989   0.82    2.48  ADVANCE_FEE_1
  0.882   1.1252   0.0000    1.000   0.81    1.40  ADVANCE_FEE_3
  0.717   0.9150   0.0000    1.000   0.79    1.82  ADVANCE_FEE_4
  1.191   1.5018   0.0667    0.957   0.74    0.01  T_ADVANCE_FEE_2
  1.957   2.2766   0.8003    0.740   0.54    0.01  T_ADVANCE_FEE_1




------- You are receiving this mail because: -------
You are on the CC list for the bug, or are watching someone who is.