Minor Update

Just doing some month end accounting. As I mentioned I switched off most but not all the systems. Glad to report that the few systems I have left on performed well in late September and my account is now positive again! Yay!

On a different note, I've performed my initial Machine Learning (Random Forest) analysis of my data set and must say the results are encouraging. Not excellent but definitely shows some potential. More to follow (eventually).

I picked some back in sept and I am up 27k on 7 of them , it touched 30k , but all came from one which is star volatility xiv picker was $18k up.

Congrats. iSystems started releasing every month some suggestions for portfolio. I have not evaluated what their criteria, but I assume it's last's month performance. Would be happy to send you if necessary.

Been away from trading for a couple of weeks due to workload. This morning i looked in on performance of my live 300 strategies. It takes time to collected data so i have not really done this before. I noticed something that i thought i share that can be a way to choose which strategies to trade. It is really simple actually. Looking back only 3 months i find that strategies that have a winrate of 60% and above have a great performance in short term . They were at 60 % performance 2 weeks based on latest 3 months live taken trades and 2 weeks later they have been doing great aswell. The ones that were at 50% performance 2 weeks ago has been losing grouped together. Looking longer term if i group the performers (1 year) the ones that are at 50 % and above is the ones that has produced the equity and the 50% and below has been losing equity all thought there are ofcourse individual exceptions but they are few.

Below is more then 1000 trades in past 3 months....

Just to confirm I understand what your saying.
Each of these charts represent the forward looking performance of a group of systems, grouped by their previous 1 year (?) win rate?

They represent the forward period performance of strategies that were grouped after their previous performance on the same period of time. To me it indicates that you should avoid trading startegies that in short lockback perspecitve are doing bad because you then have greater change of going into drawdown immediately.

That was the experience I was hoping to have!!

Anything you can say about how you choose your systems?

Hey Matt, where can I see this?

Thanks Mabi.
Have you looked at how breakout systems perform (low win rate) vs mean reversion (high win rate)?