A simple Statistial Arbitrage strategy from Quantopian

(Credit to: "Aqua Rooster", link in the algo)

This is a class of stat arb algos that I have not seen yet in QuantConnect (which just featured pairs trading algos so far). 

It consists of the following steps:

1. Select shares universe (e.g. i. a static list or ii. a dynamic one, like most liquid shares in same sector)
   and get historical prices

2. Find risk factors (i.e. common drivers for the returns), using e.g. PCA, ICA, ...

3. Regress returns vs. risk factors to get individual factor exposure (betas)

4. find shares weights such that 
        i.  maximise your alpha (e.g. z-score of regression residuals * weights) 
        ii. subject to some constraints, e.g. 
                zero net exposure, 
                gross exposure <= 100%, 
                neutralised betas 


Algo is mostly a copy & cut from Quantopian. But it is difficult to run in QC (with, say, 500 shares) since memory gets quickly maxed out. Any suggestions there?

Update Backtest

Update Backtest


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 QuantConnect. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. QuantConnect 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. All investments involve risk, including loss of principal. You should consult with an investment professional before making any investment decisions.


This discussion is closed