### Most Recent

- Is the Earth Flat?
- Worst Thing To Do On Your First Move
- who do you think is the best chess player of all time?
- How would you beat death?
- In Condemnation Of 'Long' Posts... or not...
- Tester needed for new version of chess: 4 corners
- How big an advantage does Anish Giri need to win a game?
- Criticism of Chess.com University Prodigy Program
- Why not Rf1#?
- Increase vacation

### Forum Legend

- Following
- New Comments
- Locked Topic
- Pinned Topic

Gather a dataset of IQs from individuals that play chess. Plot rating on the Y-axis and IQ on the X-axis. You should be able to see a positive/negative relationship. Or an unsupervised algo should work as well.

You should be able to specify a formula to convert IQ to expected chess rating or vice-versa using the mean and standard deviation of the two distributions. I think for IQ the mean is around 100 and the standard deviation around 15. I think that for chess the mean is around 1200 and standard deviation 200. So you work out how many standard deviations above the mean you are in IQ or chess, and your best estimate in the absence of any other information is to say you are the same number of standard deviations above the mean in chess or IQ. For example, if your chess rating is 1400, your IQ is probably 115. If your IQ is 130, you're probably capable of an average chess rating of 1600.

As a formula:

IQ = 100 + (15 x (Chess Rating - 1200)/200)

Chess Rating = 1200 + (200 x (IQ - 100)/15)