Fully automated futures trading

@isotope1 that's quite a punchy position, what does the rest of your portfolio look like? I'm running my system with manual execution and am hesitating to get back into vstoxx after the roll due to the recent volatility - i need to make it fully automatic to avoid this mental pain!
 
@algo_fool

Yeah, I think it makes up something like 30% of my short risk. Positions today are:

LVC8u3P.png
 
isotope1 said:
@globalarbtrader :

Do you clip forecasts before weighting them? Currently, my vstoxx forecasts are:

'ewmac8': -0.50
'ewmac16': -9.45
'ewmac32': -23.78
'ewmac64': -43.51
'carry': -12.88

I weight them, and then clip them, which gives me a solid -20 overall. Doing it this way improved performance on backtests iirc, but I'm now 60 contracts short here (450k, 25% vol), so not sure whether I should be OK with that or not.
More...
I don't think that you would want an individual forecast rule reach such an extreme value as -43.51 (your EWMAC64). I think that it would be beneficial to clip that.
For what it is worth: in my implementation I clip the individual rules (e.g. EWMAC64, CARRY), then clip the combined forecast (e.g. combined EWMAC forecast) and then clip the overall forecast (all rules together).
 
@HobbyTrading
ES: It was so tightly correlated with NASDAQ that I figured it was reducing diversification to have both. I tried to get as 'distant' equity indices as possible, so went with NASDAQ, SMI, HSI and Eurostoxx. Thoughts welcome though.

GE: Position was closed by the system on Friday, but it's been there all along.
 
isotope1 said:
@globalarbtrader :

Do you clip forecasts before weighting them? Currently, my vstoxx forecasts are:

'ewmac8': -0.50
'ewmac16': -9.45
'ewmac32': -23.78
'ewmac64': -43.51
'carry': -12.88

I weight them, and then clip them, which gives me a solid -20 overall. Doing it this way improved performance on backtests iirc, but I'm now 60 contracts short here (450k, 25% vol), so not sure whether I should be OK with that or not.
More...

Yes I 'clip' (I prefer winsorise as it sounds fancier) individual forecasts, combine them, and then clip them again. In this particular case you'd get exactly the same result. The reason to clip individual forecasts is to avoid too much concentration to a single source of risk (in this case a given trading rule within a particular instrument). I don't give a toss whether it improves the backtest, and the improvement is unlikely to be statistically significant.

GAT
 
isotope1 said:
@HobbyTrading
ES: It was so tightly correlated with NASDAQ that I figured it was reducing diversification to have both. I tried to get as 'distant' equity indices as possible, so went with NASDAQ, SMI, HSI and Eurostoxx. Thoughts welcome though
More...
I agree that NQ and ES have a strong correlation. However, the value volatility of the ES contract is lower than the NQ contract. So for a given amount of risk capital could you have more contracts ES than NQ. For a small account is therefore ES better than NQ, in my opinion. This criteria might not be applicable to you.
 
traider said:
does the current pysystem run with IB or did you write your own integration? Are your positions live or demo?
More...

It doesn't use pysystemtrade, I wrote everything again from scratch (thinking about open sourcing it!). It is integrated with IB. Positions are all live.
 
You must log in or register to reply here.
Back
Top