Quantopian's community platform is shutting down. Please read this post for more information and download your code.
Back to Community
Pair Trading : Having some issue with understanding the St.Dev and Profit relationship
Pairtrader V1.0
posted Apr 29, 2016
Seeking Help Pairs Trading

Hi All,

Currently I am working on a strategy for a stock with a correlation of 0.93 and is highly cointergrated (Indian stocks) , The strategy is profitable , but there are losses .
Anyways , The issue here is . There are trades where the Standard Deviation from the mean reduces , i.e the spread of the 2 stocks get much closer to the mean , but doesn't cross it and despite that it produces a loss .
Below is one such trade which occurred . It would be awesome if someone could help me out with WHY this happens , as statistically it makes sense that when the St.Dev reduces and the spread gets closer to the mean , I should profit , but sadly I seem to only profit when the -St.Dev become +ST.Dev in one days time . Below an excel file has been attached with a sample of the results .

The pattern seems to be constant . throughout , I make a loss if the I enter a trade where ST.DEV is + and by the next day if it doesnt turn into a -ST.DEV i dont make a profit . 

X   Y   LN(X)   LN(Y)   LN(X)-LN9(Y)        Mean    Std.Deviation   Z Score Trades  Buy Price   Sell Price  
950.08  191.42  6.856546192 5.254469967 1.602076225 0.018153642 -0.001512551    0.022659005 0.867919525  
1005.46 190.04  6.913200427 5.247234576 1.665965851 0.063889626 -0.000596494    0.022966553 2.807827593 SELL    190.04  1005.46  
1041.65 189.65  6.948561273 5.245180268 1.703381005 0.037415154 0.000289288 0.025828799 1.437382621 SELL    189.65  1041.65  
1016.59 192.06  6.924209168 5.257807823 1.666401345 -0.03697966 0.002458505 0.026745595 -1.474566733    BUY 1016.59 192.06  
1035.5  185.37  6.942639681 5.222353828 1.720285853 0.053884508 0.001226811 0.02773885  1.89833743  SELL    185.37  1035.5  
1011.55 187.56  6.919239087 5.234098794 1.685140293 -0.03514556 0.002420558 0.029107401 -1.290603641    BUY 1011.55 187.56  
1032.89 185.72  6.940115977 5.224240163 1.715875814 0.030735522 0.001176025 0.029713258 0.994825161  
1032.85 188.94  6.94007725  5.241429504 1.698647746 -0.017228068    0.002234233 0.030193529 -0.644585182  
1028.22 196.65  6.935584431 5.281425499 1.654158932 -0.044488814    0.000751921 0.029853684 -1.515415459    BUY 1028.22 196.65  
1035.41 198.41  6.942552763 5.290335597 1.652217166 -0.001941766    -0.000136097    0.031037957 -0.058176158  
1062.27 199.95  6.968163407 5.298067335 1.670096071 0.017878906 1.59366E-05 0.03082218  0.579549186  
1054.16 199.7   6.96049952  5.29681624  1.66368328  -0.006412792    -0.000437613    0.031004862 -0.192717475  
1079.79 195.64  6.984521857 5.276276236 1.708245621 0.044562341 -0.000508898    0.031030248 1.452493666 SELL    195.64  1079.79  
1089.28 195.35  6.993272207 5.274792822 1.718479385 0.010233764 0.00163061  0.031782763 0.270686154
3 responses
Simon Thornington
Apr 30, 2016

Perhaps the z score changed because the mean moved. I had a similar problem a while ago: https://www.quantopian.com/posts/model-slash-beta-slippage-in-dynamic-spread-mean-reversion-models

Never satisfactorily resolved it...

Pairtrader V1.0
Apr 30, 2016

Hey Simon ,

I just checkd and you were right . the mean moves . I guess using a weighted avg. mean or a longer period mean would seem to be a better option . but then we would have to compensate on the frequency of the trades ...
have u been able to identify any way to improve the condition/trades

Simon Thornington
Apr 30, 2016

Nope, this seems to be a key problem with moving mean reversion.

About Quantopian
Careers
Community
Events
Documentation
Academia
Lectures
Status
Facebook
Twitter
LinkedIn
YouTube
Terms of Use
Privacy Policy

The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by Quantopian.

In addition, the material offers no opinion with respect to the suitability of any security or specific investment. No information contained herein should be regarded as a suggestion to engage in or refrain from any investment-related course of action as none of Quantopian nor any of its affiliates is undertaking to provide investment advice, act as an adviser to any plan or entity subject to the Employee Retirement Income Security Act of 1974, as amended, individual retirement account or individual retirement annuity, or give advice in a fiduciary capacity with respect to the materials presented herein. If you are an individual retirement or other investor, contact your financial advisor or other fiduciary unrelated to Quantopian about whether any given investment idea, strategy, product or service described herein may be appropriate for your circumstances. All investments involve risk, including loss of principal. Quantopian makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances.