Quantopian's community platform is shutting down. Please read this post for more information and download your code.
Back to Community
using serial autocorrelation/momentum of strategy returns to adjust bet size?

I'm trying to do some work on bet size (empirical Kelly, etc), and investigating a rolling position sizing algorithm to grow or shrink bet size based on strategy performance. The goal is to mitigate draw-downs during unfavorable regimes without having to go and classify the regimes explicitly or learn them. However, it seems that this approach would only add value if there was in fact auto-correlation in the returns, no? Anyone have any research handy on this sort of thing?

The next step would be to make this part of a holistic position sizing strategy of strategies that did some sort of mean-variance analysis on the rolling strategies' results.

3 responses

Hello Simon,

Interesting. It's not research, but I started playing around with comparing SPY & BND here, and more-or-less convinced myself that the returns could be smoothed out, without sacrificing the average return. Perhaps the approach could be improved by sizing the "bet" based on the z-scored price difference or some other statistical measure?

Grant

This was posted by Simon on the Trading Strategy Ideas thread. It looks interesting and relevant to you:
http://www.thecambridgestrategy.com/research/2013/mar/research/the-cambridge-strategy---trade-sizing-techniques.pdf

Lol perhaps I need to reread that paper!