It is said that Edward O. Thorp was able to harness small correlations for reliable financial gain. I've seen some strategies based on strong correlations which did not seem particularly reliable. Does anyone have an idea or a paper to how the small correlation exploitation could work? I can only think of some kind of relative value arbitrage.

  • $\begingroup$ Sounds like something that a marketing person wrote. $\endgroup$
    – John
    Apr 14, 2014 at 21:58
  • $\begingroup$ @John or not? ... I read that very same sentence on wikipedia without any further evidence, so I was just curious what stands behind such claim. $\endgroup$
    – Paya
    Apr 14, 2014 at 22:36
  • $\begingroup$ What I meant is that someone could have misinterpreted something. For instance, they could say he uses small correlations for financial gain, but they also could say he diversifies. Who knows what they really mean. I wouldn't worry about it too much. $\endgroup$
    – John
    Apr 14, 2014 at 22:47

2 Answers 2


it is based on Kelly criterion. mentioned in one of stackexchange posts here .

  • $\begingroup$ Could you please provide an example/paper how I can use it for reliable returns when I know the correlation is not 0? I can't wrap my mind around it... $\endgroup$
    – Paya
    Apr 10, 2014 at 21:10
  • $\begingroup$ The system helps to choose the optimal allocation between stocks. It does not choose stocks for you. You have to select your basket. It is iterative system. It takes time to converge to optimal allocation. Do not expect to get it working in 3 trades. Also, it helps to have stocks with minimum correlation. With perfectly correlated stocks - any allocation will give the same result. The detailed description is here. $\endgroup$
    – dkhokhlov
    Apr 11, 2014 at 3:55
  • $\begingroup$ But how does this strategy benefit from small correlations? As far as I understand it, high correlation is bad, but if it's small or 0, then it's better. I thought Thorp somehow exploited the weak correlation relationship itself, rather than just building a system which expects uncorrelated assets, didn't he? $\endgroup$
    – Paya
    Apr 11, 2014 at 4:37
  • $\begingroup$ After some further research, this does seem to be the correct answer. Thorp did a lot of research in this area and the gain earned through continuous rebalancing (volatility pumping) is highest when correlation is 0. Thanks for pointing me to the right direction. $\endgroup$
    – Paya
    Apr 15, 2014 at 0:22

Correlations between what?

Correlations between stock A and another stock B - relative value arbitrage - not sure if small correlations will help here.

Correlations between stock A and its future stock return Ra - its called Information Coefficient. Try Fundamental Law of Active Management and many similar web info on Fundamental Law for more information.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.