Strategy performances decline over time?

d08 said:
That requires a lot of confidence in the strategies. I've seen them go into a drawdown, then into deeper drawdown, then record drawdown and then sideways for years.
More...
Agreed. The guy is more of a short term swing trader I believe, so I think it's easier for him to make these adjustments.

Here is the podcast. I'm not advocating any of his stuff, but what he is saying makes lots of sense, especially for short-term trading, imho.

http://bettersystemtrader.com/161-i...strategies-that-manage-strategies-david-bean/
 
Usually performance must decrease over time, for the simple reason that strategies are designed based on working great in the past.
For example let’s say that you’re a psychic and you know how the next 100 trades of a given strategy will perform. Do you then choose a strategy that will perform better based on the past 100 trades, or based on the future 100 trades? (assuming that it cannot work identically over every 100 trades)
If you choose a strategy that performs best based on the past 100 trades then you’ve automatically chosen to decrease your performance in the future. But if you choose the strategy that works best in the future, then you probably wouldn’t have chosen it in the first place because it didn’t perform best in the past. And you especially wouldn’t have chosen it without actually knowing that it will work better in the future.
 
qlai said:
Agreed. The guy is more of a short term swing trader I believe, so I think it's easier for him to make these adjustments.

Here is the podcast. I'm not advocating any of his stuff, but what he is saying makes lots of sense, especially for short-term trading, imho.

http://bettersystemtrader.com/161-i...strategies-that-manage-strategies-david-bean/
More...

I'm not saying it's necessarily a bad idea, I've tested some equity curve trading strategies but could never make it worthwhile to use in real trading.
 
TZT said:
I have traded historical-data-backtested strategies since 1999, in stocks, futures, and funds. Once I have discovered and implemented a profitable trading strategy, its performances always got worse and worse over time. None of my strategies remained profitable after 10 years.

I am curious whether other strategy traders have seen the same pattern? And how your guys manage this issue?

For me, I generally start to reduce my position in a strategy if it is unprofitable for a year. If the strategy remains unprofitable for another year or two, I stop trading it altogether. [My strategies usually generate dozens of trades a year; so a couple of years give me enough sample to suspect that the world has changed.]
More...

Instruments change. Components change. Major indexes alone are not what they were 20 years ago. I trade instruments that didn't even exist 5 years ago. So to expect any strategy to remain constant is an unrealistic expectation.
 
Not only do instruments change, but the major market forces and logic around them also change as well. With the rise of passive investing the ones moving the markets are not the Joe public, but the actively trading machine algorithms. From the days of technical analysis and spread trading to the machine learning algorithms that seem to train themselves and choose trades I would never take myself its just mind-boggling the shift in strategies. We have seen a silent tradings arms race since 2008. Its only in the last few years has the public really started to take notice and materially participate.

So to tie into the topic, I think strategies decline as the logic behind what made them work in the past becomes less human-driven.
 
Any second now, somebody is going to suggest that I buy the worst DOW30 performers of 2019, and hold them through 2020, and I'll have made money. "Absurd!"

And then, someone else will observe as how, once an idea becomes known, capital will rush to it, dilute its effectiveness for all takers, and cause participating capital to wander off in search of the next opportunity to arbitrage between expected risk and expected reward.

And the babe cries. And the old man sighs.
The sun sets low and rises again.
The Moon for its part keeps its face steady towards us,
like a well-managed ETF.



("Awwwww! That was beau-ti-ful!" :rolleyes:;):D )
 
The only strategies which are guaranteed to fail over time are the curve-fitted ones. Which is to say almost all of them. The remaining few may fail on a specific market which has itself materially changed, but continue to work on the others which have not.

Trading styles however just respond to the dynamics of a market which is free to function, and as long as price rises and, falls and trends, must continue to perform.
 
If your trading strategy is having poor results, then I think that you need to work on it. Figure out what exactly is not functioning in it. Analyse your lose deals in order to figure out what needs to be improved
 
You must log in or register to reply here.
Back
Top