Fully automated futures trading

[Same Lazy Element]

Seems like VSTOXX got put together in the same group as bonds, which is weird.

Both vol indices and bonds are risk-off assets, so it make sense they go into the same bucket

Side note: short VIX/V2X + long bonds works as a hedged carry trade of sorts if you use term structures for each as a signal, though I have not thought about that trade in zero/negative yield environment

 

[Kernfusion]

Since Elder brought it up, I've been playing with Rob's handcrafting method for a few weeks now, trying to understand the results I'm getting.

Here's what I get for 12 instruments (returns data for the date range 2015/07/01-2020/07/01) that I think are somewhat diverse, representing each group (stocks, bonds, vol, aggs, metals, stir):

                    ZC      V2TX        GE       MXP    ESTX50        NG        PL        HE       GBP        ZS       GBM        ZF
Vol weights   0.036196  0.143411  0.113382  0.085424  0.099760  0.083576  0.077732  0.040960  0.069278  0.030971  0.141333  0.077977
Std.          0.190274  0.439473  0.008014  0.145823  0.219591  0.380968  0.266162  0.340262  0.103737  0.166355  0.019816  0.027569
Cash weights  0.007006  0.012019  0.521088  0.021576  0.016732  0.008080  0.010756  0.004434  0.024596  0.006857  0.262684  0.104172

There's a 52% cash allocation to Eurodollar, which really seems odd. This was ran with no risk target, natural risk came out at 1.38%.
I then looked at the subportfolios:

['V2TX', 'GE', 'GBM', 'ZF']
['MXP', 'ESTX50', 'PL', 'GBP']
['ZC', 'NG', 'HE', 'ZS']

Seems like VSTOXX got put together in the same group as bonds, which is weird.
I then looked into the correlations, which somewhat explains how that happened:

              ZC      V2TX        GE       MXP    ESTX50        NG        PL        HE       GBP        ZS       GBM        ZF
ZC      1.000000 -0.064267 -0.121516  0.170380  0.150131  0.016875  0.049561  0.265098  0.154059  0.629425 -0.117282 -0.129847
V2TX   -0.064267  1.000000  0.370536 -0.411786 -0.769686 -0.106653 -0.313154 -0.158634 -0.312296 -0.078578  0.175712  0.420393
GE     -0.121516  0.370536  1.000000 -0.057798 -0.406423 -0.142400 -0.001980 -0.172233 -0.104512 -0.100224  0.605351  0.949195
MXP     0.170380 -0.411786 -0.057798  1.000000  0.498750  0.122098  0.425653  0.210096  0.357280  0.250902  0.057800 -0.081791
ESTX50  0.150131 -0.769686 -0.406423  0.498750  1.000000  0.108295  0.361960  0.249286  0.326445  0.199973 -0.127219 -0.454780
NG      0.016875 -0.106653 -0.142400  0.122098  0.108295  1.000000  0.073907  0.129099  0.053497  0.112193 -0.091922 -0.132716
PL      0.049561 -0.313154 -0.001980  0.425653  0.361960  0.073907  1.000000  0.162243  0.415357  0.132317  0.122485 -0.013490
HE      0.265098 -0.158634 -0.172233  0.210096  0.249286  0.129099  0.162243  1.000000  0.118090  0.275095 -0.073586 -0.196772
GBP     0.154059 -0.312296 -0.104512  0.357280  0.326445  0.053497  0.415357  0.118090  1.000000  0.161429 -0.056220 -0.061670
ZS      0.629425 -0.078578 -0.100224  0.250902  0.199973  0.112193  0.132317  0.275095  0.161429  1.000000 -0.110987 -0.105146
GBM    -0.117282  0.175712  0.605351  0.057800 -0.127219 -0.091922  0.122485 -0.073586 -0.056220 -0.110987  1.000000  0.617952
ZF     -0.129847  0.420393  0.949195 -0.081791 -0.454780 -0.132716 -0.013490 -0.196772 -0.061670 -0.105146  0.617952  1.000000

Do others get similar results? I could try to "fix" these by running with a higher risk target, but I'd like to understand what's happening before I do that, and also, how to determine the risk target I should be running with. Without leverage, max risk that this portfolio can reach is about 7.5%. My system is based off of Rob's Leveraged Trading book so there's a leverage factor built in the system in the form of instrument_risk_target / instrument_risk.

Well, "what risk target?" part of the question is easy: if you believe in Kelly formula then your risk target should be equal to your Sharpe ratio. That's really why we do backtesting in the first place - to know our Sharpe ratio. Of course the problem is that we never really know our "True Sharpe ratio", backtest only gives us historical estimation, so a safe thing to do is to assume that you'll only get half of it in real life. Also, if you run at full Kelly, some people say that even though it's optimal in terms of increasing your long-term geometric return, it's a rough ride, hence the "half-Kelly" rule. So here you go: your backtest Sharpe is 1.0, divide it by 2 two times and you get the 25% "correct" risk target..

 

[wopr]

Well, "what risk target?" part of the question is easy: if you believe in Kelly formula then your risk target should be equal to your Sharpe ratio. That's really why we do backtesting in the first place - to know our Sharpe ratio. Of course the problem is that we never really know our "True Sharpe ratio", backtest only gives us historical estimation, so a safe thing to do is to assume that you'll only get half of it in real life. Also, if you run at full Kelly, some people say that even though it's optimal in terms of increasing your long-term geometric return, it's a rough ride, hence the "half-Kelly" rule. So here you go: your backtest Sharpe is 1.0, divide it by 2 two times and you get the 25% "correct" risk target..

Thanks!
I see now my question wasn't clear, I meant what risk target in the bootstraping code Rob made, shown here https://qoppac.blogspot.com/2018/12/portfolio-construction-through_14.html
In this call

p = Portfolio(returns, risk_target=0.1)

I played with it a bit, and from what I see, if you allow leverage you it will run as if you didn't provide any risk target and then just multiply by a factor to hit the risk you passed in, but volatility weights will be the same.

My target risk for the entire portfolio is 24%, and I got to that pretty much using the exact method you described above

 

[Kernfusion]

It's been quiet here lately, I guess Rob is on one of his vacations
I'm being hammered, lost about 7%, seems to be across the board..

 

[HobbyTrading]

I'm being hammered, lost about 7%, seems to be across the board..

I had several new "high water marks" in late July and the first week of August. Those high water marks were mainly driven by gold and silver. But then the party ended and I'm now down about 15% from the high water mark.

 

[globalarbtrader]

It's been quiet here lately, I guess Rob is on one of his vacations
I'm being hammered, lost about 7%, seems to be across the board..

I was on one of my vacations Got back from France last week, and thanks to the UK governments superbly efficient COVID response* I am currently several days into a two week quarantine. That doesn't affect my life very much, as my commute consists of a one minute long stroll to the bottom of my garden, although I do miss cycling outside (does anyone have the worlds smallest violin to hand?). I've basically been living under lockdown conditions for the last 7.5 years.

* Yes we are the envy of the world, with one of the highest excess deaths per million in the world, and one of the largest forecast drops in 2020 GDP in the OECD.

Didn't do anything productive last week. Yesterday I did the show notes for the latest TTU global macro podcast, then started on pysystemtrade (which you will recall now forms my main futures trading system). I fixed a couple of bugs, and then restarted work on the implementation of my execution algo. Then stopped work on that, and started refactoring the horrifically obtuse code that basically translates IB order objects into mine (decided it was easier to refactor rather than trying to understand what the hell I'd done the first time round).

But performance, you want to know about performance. Well yes, performance hasn't been great. Similarish figures to others, 13% drawdown something like that, up about 7% for the calendar year now and probably down about 2% for the tax year.

On the upside the long only stuff is ripping away (at least on an absolute basis; my underweight to US equities hasn't looked too clever), so the diversification is there. Still, the futures underperformance is a motivation to keep working on pysystemtrade, so that eventually I can implement some new systems and add a little bit of Sharpe here and there.

GAT

 

[Elder]

Well its always good to have some returns dispersion amongst this group. So far my system seems to be holding up (although reports of drawdowns amongst others in this thread, has served as an omen in the past). I was up 17.4% ytd as of last night touching a new HWM, but down ~ 1.5% so far today. As mentioned previously quite a lot of my recent returns have come from the vertiginous climb of the NASDAQ, so I keep holding my breath for a brutal drawdown.

Separately, I have also been listening to the TTU macro series, which I find compelling listening, and would recommend it to anyone following this thread, but hasn't yet tuned in. There have been some great guests on the show all with excellent insights.

 

[globalarbtrader]

Well its always good to have some returns dispersion amongst this group. So far my system seems to be holding up (although reports of drawdowns amongst others in this thread, has served as an omen in the past). I was up 17.6% ytd as of last night touching a new HWM, but down ~ 1.5% so far today. As mentioned previously quite a lot of my recent returns have come from the vertiginous climb of the NASDAQ, so I keep holding my breath for a brutal drawdown.

Separately, I have also been listening to the TTU macro series, which I find compelling listening, and would recommend it to anyone following this thread, but hasn't yet tuned in. There have been some great guests on the show all with excellent insights.

Glad to hear someone is profitable.

As an aside, I am going to be on the systematic investor TTU this weekend. So if anyone has any topics they want me to discuss, let me know.

GAT

 

[wopr]

Pretty much same here, current drawdown is about 13%, for me it's also across the board.

As an aside, I am going to be on the systematic investor TTU this weekend. So if anyone has any topics they want me to discuss, let me know.

Anything but using risk to adjust position size, that horse has been dead for a while now
On a more serious note, I'd be interested to hear the update on the idea you mentioned on the podcast a few months ago, of using forecast strength to select which markets to trade so you can trade more markets in the smaller account size. With the recent move to pysystemtrade and work involved there, I understand there might not be any updates on that idea though.

 

[Elder]

Glad to hear someone is profitable.

As an aside, I am going to be on the systematic investor TTU this weekend. So if anyone has any topics they want me to discuss, let me know.

GAT

So here is one, which I am not sure you have previously encountered during your stints on TTU, but it has been a hot topic on TTU in the past. One or two of the previous hosts have often argued that institutional investors should allocate a much higher percentage of their assets to TF. If memory serves me correctly, they might have even suggested that perhaps the majority of capital should invested using TF strategies. If this were to happen wouldn't the TF risk premium disappear?