Fencer: Quote: "I'll improve the BKR formula by adding some penalties for repeated games between the same players". He he, shouldn't that be "change" the formula? I'm not sure about that word "improve". ;-)

I echo Walter's words. Some people's style of playing is to play all and sundry, perhaps playing mostly tournaments, or just inviting a wide range of people to games. Others' style is to find a few partners who are a pleasure to play and chat with - and then stick with them by and large. These people would be penalised by this proposed formula change.

We were discussing this issue on the backgammon board. "The simple pattern seems to be a pair who play together with a very unbalanced win/lose ratio brought about by a suspicious amount of resigning and with one or both having high ratings. As more nicks are brought into the scam, detection would become increasingly difficult but a significant level of resignations would still be a good indicator. It would ease the server burden if checking were restricted to the top X% of players."

I think detection is a better system for the site, though it's obviously a lot more work for you to program. One solution would be to keep an eye on resignations, as these seem key to the cheating method (perhaps in conjunction with the number of moves made). These could then be brought to the attention of a special moderator who would look into the matter. To avoid detection the cheats would have to stop resigning the games and play them through to a conclusion. They could still fix the outcome, of course, but it would be a lot more work.