Deadline June

[meanreversion]

I want to add this. If you see that one system is better than another based on the metrics he's suggesting, this doesn't mean you should discard the worse system. You should keep it and trade them both. Diversification is also important. If you don't have enough money to trade them both, then of course you trade the best one.

Fully agree with that sentiment. Diversification comes in adding systems, not markets. However, the more systems, the more capital required! Darn..

 

[Yamato]

Yeah, but since diversification allows you to increase profit faster than you're increasing drawdown, you will be needing relatively less capital per system than if you were trading just one system.

 

[meanreversion]

That's an excellent point. It might also be worth looking at correlation of returns between the two systems - in an ideal world, it would be close to zero.

 

[Adamus]

"That's because I can't tell you quantitatively what I'm looking for"

sorry but if you haven't got a target return and volatility / max drawdown in mind, how do you know when to stop looking?

also the scribd thing, i looked and you can upload something instead. But really, you should be able to find it somewhere. it took about 15 seconds to find that one, there must be more.

The answer to that is long and many books have been written about it. If you aren't already a mechanical trader and system developer, I'd suggest starting wtih Robert Pardo or Bruce Babcock's work.

re scribd - I paid the £3 - the book certainly looks interesting.

 

[meanreversion]

I think you've completely misunderstood what DashRiprock said, try reading it again.

 

[DashRiprock]

The answer to that is long and many books have been written about it. If you aren't already a mechanical trader and system developer, I'd suggest starting wtih Robert Pardo or Bruce Babcock's work.

re scribd - I paid the £3 - the book certainly looks interesting.

i think you misunderstood my question... meanreversions advice is bang on i think.

what i think you should do is start with a blank piece of paper and try to explain to yourself how the markets work and why they do what they do.

then pick one measurement like sharpes ratio or sortino or whatever, and a threshold in this target that are happy to trade

and then devise a system that starts from the piece of paper and makes it past your threshold.

and then you will either make money or lose money.

 

[Adamus]

Selecting systems

Right, allow me to make a few observations. If you want me to leave this thread, please tell me, but I'd like you to consider the following.

Of course you can. I started a public thread with the aim of receiving outside input.

I'm going to split this up because the conversation on this thread is shooting ahead faster than I can read it and currently I'm under time pressure and I know I will probably repeat what someone else is about to say.

1. You've been working at this some time now, and don't seem to have settled on a system. In my experience, the main reason that people can't find a system after extensive backtesting is because they don't have quantitative metrics to compare systems. At no stage have you mentioned return divided by drawdown, or Sharpe (return divided by vol of returns). I fail to see how you can compare systems without using one of these two metrics.

(You mention profit per trade and drawdown in the same sentence.. this is not the same as CAR/MDD, because you have not included frequency of trading, i.e. you aren't incorporating a time element.)

I don't believe you can confidently choose between systems in a short space of time - you need to fix this.

Thanks for the observation but you're wrong unfortunately after having written it so nicely. I think you speed-read or skim over a lot of my posts - in fact I think you have said as much yourself on occasion.

I don't use Sharpe. I would use Sortino, but I can't calculate it quickly enough as yet.

I select my systems by taking several different factors into consideration.

One of them is in fact net profit / drawdown - I posted some results with that in one of the columns earlier this weekend, I'm sure.

 

[meanreversion]

The answer to that is long and many books have been written about it. If you aren't already a mechanical trader and system developer, I'd suggest starting wtih Robert Pardo or Bruce Babcock's work.

Your answer is revealing. You seem to think that comparing systems is inherently complicated - it isn't. You have no way of deciding between systems, thus by definition you'll almost certainly never find one that you're happy with.

 

[Adamus]

Equity curves

2. Looking at the equity curve is important to you, BUT your eye will see what it wants to. If you're testing something and are quite keen on it, you'll look at the curve and see how it's always rising. An investor might look at it and see all the dips that your brain skipped over.

I disagree. Do you mean ME personally or anyone & everyone? I believe I can be objective enough to avoid the pitfall you outline there.

 

[meanreversion]

Re: Selecting systems

One of them is in fact net profit / drawdown - I posted some results with that in one of the columns earlier this weekend, I'm sure.

No good.

You need annual return / drawdown.

Net profit will of course change depending on the sample period (which I will assume is not always the same!)

 

[meanreversion]

Re: Equity curves

I disagree. Do you mean ME personally or anyone & everyone? I believe I can be objective enough to avoid the pitfall you outline there.

Sorry, but you're kidding yourself.

 

[Adamus]

Money management, drawdown, portfolios

3. Higher profit does NOT mean a better system. If system A has a return of 60% a year with a drawdown of 40%, this is WORSE than system B, which returns 20% a year, with a drawdown of 10%. Why? Because all you need to do is trade system B in three times the stake size, and hey presto, it's better than system A. This confirms my belief that you're not completely clear in your own mind on how to compare systems quantitatively.

What confirms your belief about my selection processes? I do relative bet size selection within the basket of instruments I run a system against. I don't do it in backtesting, because I look at the results on an individual instrument basis anyway and I only put together a portfolio analysis after I'm satisfied with all that. That's probably why I don't mention it much on this thread.

That means I don't even have a definitive capital allocation as an input parameter to my backtesting result analysis, so I don't see any percentage numbers like that. Well I do because NinjaTrader is set to show percentages by default. But I just look at the raw dollar return per $100,000 lot backtest run. This means I can directly compare results (and I don't mean just profit!) between systems, despite the fact that I could input a starting capital and show a CAGR.

Does this give you a better idea of what I'm doing?

By the way you never told me what MAR stands for.

 

[meanreversion]

Managed Account Report, I think, it's a newsletter for CTAs.

Ok, I'll lay off.. I just feel that you're spinning your wheels a bit, and it's frustrating to me (I have no idea why!!).

 

[Adamus]

belief

4. You will not be able to trade a system unless you believe in it, and for you to have belief, you need to have a rationale, or a theory, or something. Simply finding a pattern and assuming it will continue is completely bogus.

DashRiprock has made comments along similar lines. My advice to you now would be

- be clear in your mind precisely how to quantitatively compare systems
- trade your beliefs.. what do you believe about the market and the way it acts, and design a system around this
- please forget this gap system (GBP/AUD gaps - are you serious?)

I do have a belief in the systems I trade but it's not based on a rationale of the kind you want, as I said before. Whether it's bogus or not is something that I do a lot of testing to determine and my hard drive is littered with the well-tested remains of bogus systems.

I'm already doing your first two bullets there - but I'm afraid the decision on the last one will be made based on the stats I produce this week.

PS I should post a link to that conversation we had last year about the forex crosses I trade - then instead of saying anything, we can just post that link.

 

[meanreversion]

Does Ninja allow for stake size as percentage of equity?

 

[brettus]

Re: belief

I do have a belief in the systems I trade but it's not based on a rationale of the kind you want, as I said before. Whether it's bogus or not is something that I do a lot of testing to determine and my hard drive is littered with the well-tested remains of bogus systems.

I'm already doing your first two bullets there - but I'm afraid the decision on the last one will be made based on the stats I produce this week.

PS I should post a link to that conversation we had last year about the forex crosses I trade - then instead of saying anything, we can just post that link.

With backtesting your strategies, do you find that if you change the stop loss take profit values slightly, that the strategy fails. I would only use a system that works on many values around the optimization.

 

[Adamus]

Re: Equity curves

Sorry, but you're kidding yourself.

I beg to differ. Honestly. I walked away from your statement and came back three times and asked myself, am I really kidding myself?

So I think we've taken this conversation as far as it will go guys (Jacob and Dash) - you're spending your time telling me a lot of stuff I already internalised a while ago, and you're making assumptions that aren't helping here.

Thanks anyway. If I see the light, I'll let you know.

 

[Adamus]

Managed Account Report, I think, it's a newsletter for CTAs.

Ok, I'll lay off.. I just feel that you're spinning your wheels a bit, and it's frustrating to me (I have no idea why!!).

No, you had CAGR/MAR as a stat. It was another thread. If I can dig it out, I'll post the link.

 

[meanreversion]

Er, I don't recall that. Return/drawdown, sometimes referred to as the MAR ratio, or Calmar ratio.

If I did type CAGR/MAR then I'm confusing myself with acronyms.

 

[Adamus]

serirously my last post today (MAR)

Er, I don't recall that. Return/drawdown, sometimes referred to as the MAR ratio, or Calmar ratio.

If I did type CAGR/MAR then I'm confusing myself with acronyms.

No I think it was me who confused it just now. Here's the post (I'm getting a serious case of deja vu):

Sorry, I don't think looking at an equity curve helps, because the eye sees what it wants to. Also, most people run backtests and look at equity on a linear scale.. log scale makes far more sense.

Return/drawdown (or MAR ratio) is a good one. I don't think I've ever seen anyone mention this on t2w.. the assumption is if that system A returns 100% and system B returns 50%, then without question system A is better.. what b0ll0cks.

MAR? Is it any of these: http://acronyms.thefreedictionary.com/MAR