Search results

As much as I enjoy feedback from people without a clue, yet a feeling of great self-importance, please don't post to this thread if you intend to be rude while adding absolutely nothing useful to the discussion. Why would anyone PM you about this? It's pretty obvious that you have nothing...

You are obviously correct that it is pure curve fit, since the system performs poorly on all the out of sample data (both before and after) the test period that was posted. -bulat

That's true, but it brings up a whole new set of problems. Bonferroni correction simply requires an ever more stringent level of statistical significance as the number of hypotheses tested goes up. But if you are doing large scale data mining, where you are searching billions of patterns, then...

And what would the analytical approach that can separate the valid patterns from noise consist of?

I don't know where you are getting this from. Of all the successful traders that I know, most trade longer time frames (days to weeks). That's not to suggest that there are no successful daytraders, but I don't see them as the majority of successful non-professional traders.

Here's an interesting academic paper which also talks about the near impossibility of automatically identifying valid trading patterns, even when you know for sure that they exist in the solution space that you are searching (which you actually dont know)...

If you have a particular idea about some market behavior, then code it without doing extensive optimization, and find that it produces outstanding returns while passing various statistical significance tests, you almost certainly have a winner on your hands. If you evaluate 1,000,000 random...

Are you saying this because you've actually achieved meaningful results in real trading through a system developed via data mining or is this purely theoretical? -bulat

I've spent a lot of time thinking about using various automated methods to discover trading patterns/strategies and I'm coming to the conclusion that it's mathematically impossible. When you apply some automated discovery mechanism you either have no preconceived notion or only a very general...

Have you used it? It does look interesting. I'd be curious as to how complicated it is to get started it (looks pretty dense). Also, are there any major limitations? bulat

Are there any real alternatives for system developers to WealthLab and TradeStation? Both of these are tied to brokers, and Tradestation has an annoying monthly fee to boot. I've been using Amibroker, but writing systems of any complexity in it is no picnic. I like what I saw in Wealthlab...

What about tick charts? Do you find any use for those, or do you just stick with minute charts? One of the things I find most annoying with minute charts is how the deal(or rather don't deal) with overnight gaps. The other obvious advantage is the breaking down of huge bars during price spikes...

AMT4SWA, do you only go as low as 5 min charts, or do you ever drop down to lower timeframes? It seems like a 3 min chart usually has enough range for some decent moves, but with the advantage of more trades on any given day.

You've got a pretty interesting system with the zero and 1/2 crosses. I dont think I've thinking anything like that before. How did you come up with something like this, was it purely chart observation? Are there any other basic principles that you base your systems on? -bulat

If you could describe this process at some point, I am sure that many of us would be very interested and grateful for the contribution. I've also used neural nets to mine data in the past, and have found them to be insanely time consuming. Any way to achieve the good result with less time...

Sorry if this is off topic, but might I ask what you consider to be better than neural networks? -bulat

Are your entry points pre-computed before the market opens, or does your system compute them as the day unfolds? bulat

With so few trades per day, why dont you trade your other five systems as well? Something like a volatility breakout system would do quite well in this environment. bulat

How can you have as many intraday trades as you posted today based on daily bar data systems?

Just glancing at the chart, the % levels havent changed all that much. Hence the contraction in daily range is no big deal, as it's clearly just a reduction in the value of the contract, and not so much a contraction in volatility. An increase in the number of contracts traded will compensate...