Thanks for the interest. If enough people want it, I might share the code at some point, possibly behind a low‑cost paid tier. That said, I plan to keep the articles themselves free.
What if you don't have a core system, just hundreds more or less (un)correlated small edges like seasonality, mean reversion, momentum, ... which have the same problem: very small number of trades each, hardly any varition most of the time, some trades of systems in groups of similar systems overlap but some groups do not, especially not between groups? What would the approach be in this case? How would one size positions and construct something else than an equal weight portfolio of these kind of edges? I use equal weight 1/N and depending on N (max open positions) I manage exposure and draw down. Higher N lower drawdown and lower CAGR...
Thanks for the thoughtful question. Two things worth checking.
First, capital efficiency: with many small infrequent edges, the binding constraint isn’t N in the abstract but how many strategies are simultaneously in-market. That determines your actual capital requirement and effective leverage at any given moment.
Second, even without an explicit core, you likely have one implicitly. Regress your combined system returns against SPY — my guess is you’ll find a substantial positive beta. Your core strategy is probably the stock market, and N is managing the decoration around it, not the underlying risk.
Hope that gives you a useful starting point. Happy to dig deeper if you want to share some numbers. Cheers, L.
Thanks for the great post!
Would it be possible to share the notebook for this analysis?
Thanks for the interest. If enough people want it, I might share the code at some point, possibly behind a low‑cost paid tier. That said, I plan to keep the articles themselves free.
Very insightful. Thanks.
What if you don't have a core system, just hundreds more or less (un)correlated small edges like seasonality, mean reversion, momentum, ... which have the same problem: very small number of trades each, hardly any varition most of the time, some trades of systems in groups of similar systems overlap but some groups do not, especially not between groups? What would the approach be in this case? How would one size positions and construct something else than an equal weight portfolio of these kind of edges? I use equal weight 1/N and depending on N (max open positions) I manage exposure and draw down. Higher N lower drawdown and lower CAGR...
Thanks for the thoughtful question. Two things worth checking.
First, capital efficiency: with many small infrequent edges, the binding constraint isn’t N in the abstract but how many strategies are simultaneously in-market. That determines your actual capital requirement and effective leverage at any given moment.
Second, even without an explicit core, you likely have one implicitly. Regress your combined system returns against SPY — my guess is you’ll find a substantial positive beta. Your core strategy is probably the stock market, and N is managing the decoration around it, not the underlying risk.
Hope that gives you a useful starting point. Happy to dig deeper if you want to share some numbers. Cheers, L.