Fully automated futures trading

HobbyTrading said:
Rob, I have read your latest blog entry (https://qoppac.blogspot.com/2020/10/should-i-run-my-trading-system-at-fixed.html) but have problems with the conclusion, and thus with the question in the title of it.
You seem to reject the usage of a fixed risk target such as you recommended in your book "Systematic Trading". You now suggest to use something else:
I don't completely understand what you mean by this. Can you please give an example how you would implement this? e.g. for one instrument, or for a portfolio of instruments?
More...

No I am saying what I do in Systematic trading is correct.

Will explain in more detail on Monday

GAT
 
Could I check if anyone has experience developing Rob's system in Saxo using its API? I was looking at Saxo and it seems to be the only broker where I live (Singapore) that offers a wide range of dated CFDs (non dated are crazy expensive). Checked it out as per some of Andreas Clenow's posts. Unfortunately, unlike IB (ib_insync, ibridgepy, tws api), I don't see people developing frameworks for Saxo. Would be great if someone has experience with Saxo and could shed some light on this.
 
Same Lazy Element said:
Do you think the word “correct” applies to anything in the systematic investment space? I always feel that I am picking the least wrong option, whenever you’re making any choices. Hell, it’s even hard to say that something was a correct choice a posteriori IMHO.
More...

Good point. I meant the evidence in the blog post is consistent with the system presented in the book.

GAT
 
globalarbtrader said:
No I am saying what I do in Systematic trading is correct.

Will explain in more detail on Monday

GAT
More...
In that case I must have misunderstood the first portion of your conclusion:
The simpler fixed risk target idea, where we target 25% annualised risk or whatever every single day, is a non-starter. It dramatically reduces performance with no clear benefit to other characteristics of the strategy, apart from the more predictable realised risk. And the reason why is clear; it throws away the information provided by aggregate forecast strength, which is a clear predictor of future risk adjusted return.
More...
Systematic Trading sets the risk target at a fixed value, and explains why half-Kelly (i.e. 25% annually) is a good choice.
 
HobbyTrading said:
I
Systematic Trading sets the risk target at a fixed value
More...

The simpler fixed risk target idea,where we target 25% annualised risk or whatever every single day, is a non-starter.
More...

The key part of that quote is "every single day".

The system described in Systematic Trading has an average annualized volatility target that is fixed, but it does not attempt to hit that target every trading day, or every year for that matter, only over the long-run. Expected vol will be higher for some time periods and lower for others, depending on the combined forecasts for each instrument.

Rob's recent blog post was investigating the effect of trying to hit that vol target every day.

Apologies to Rob if I've misstated anything.
 
tgibson11 said:
The key part of that quote is "every single day".

The system described in Systematic Trading has an average annualized volatility target that is fixed, but it does not attempt to hit that target every trading day, or every year for that matter, only over the long-run. Expected vol will be higher for some time periods and lower for others, depending on the combined forecasts for each instrument.

Rob's recent blog post was investigating the effect of trying to hit that vol target every day.

Apologies to Rob if I've misstated anything.
More...

That's pretty much it, with the added factor that differences in position and correlations will also cause expected risk to deviate from the long run target (what I call RCF in the post).

Thanks I won't have to come back to this on Monday after all...

GAT
 
tgibson11 said:
The key part of that quote is "every single day".

The system described in Systematic Trading has an average annualized volatility target that is fixed, but it does not attempt to hit that target every trading day, or every year for that matter, only over the long-run. Expected vol will be higher for some time periods and lower for others, depending on the combined forecasts for each instrument.

Rob's recent blog post was investigating the effect of trying to hit that vol target every day.

Apologies to Rob if I've misstated anything.
More...
Thanks for that clarification.
What remains is that I still don't understand from the blog post how the system can be improved.
 
You must log in or register to reply here.
Back
Top