Hahaha! +1

Once @Lekkim used the word "volume" everybody went berserk... In post #43 @Rosalieone brought up an interesting article illustrating tick frequency could be a proxy for trade volume, but nobody was listening anymore. @ryuryu, @W0lfram, @RickM, ...

Thanks for the info. Based on post #108 these levels would be between 0.1 and 0.15 * ADR * sqrt(hour +1). Time for some experimentation...

Absolutely! Suppose I have been "mining" random strategies for a couple of days using a certain set of possible indicators to randomly choose from, then to test the Null Hypothesis on randomized synthetic time series, I should also mine these during ...

People have tried to create cointegrated currency baskets. For example @7bit tried that in the thread "Synthetic hedges, cointegration, mean reversion and similar stuff". He eventually gave up, because he was unable to find a stable basket. If you ...

For optimizing for today's market, you should indeed only use the last few months/years, not all historical data you can get your hands on. Would having more history help when doing a Walk Forward Analysis? That way, you can do more "steps" and thus ...

Yes, indeed. Things have changed dramatically over the years. I once bought historical M1 data going back to 1987. Ranges, momentum, etc. are completely different from todays market. In other thread on FF, @robots4me suggested to do a WFA based on ...

Hahaha. Fair enough

Nice curve. Yes, after 8 years this thing has certainly proven it has an edge and wasn't merely luck. How about after 4 years? After 2 years? First year? When are we confident this thing is actually making money and not just lucky?

Cool! Nice to see my code inspired you to improve on that and make something more advanced! Interesting experiment. I doubt that running a portfolio of 10,000 random EAs will be anything else than random, but doesn't hurt to try. Adding a fixed SL ...

I am not sure what you are trying in your experiment? Keep in mind that the EA in post #1 really trades randomly. Backtests have no relevance for forward tests.

Will a worthwhile strategy with an edge outperform all random strategies? I guess it will outperform, say, 90% of them but some random strategies will still be better. Or do you expect it to outperform significantly, say, 99.9% of the random ...

What do you mean?

Interesting way to visualize the performance! Thanks. In the image it reads "compared to 10000 random strategies with the same risk". What does that mean? Do they make random equity curves based on your trades (i.e. Monte Carlo simulation)? Do they ...

Thank you. Good suggestion! I remember reading a long thread by AlgoTraderJo where he describes that the "measures" data-mining bias by running his data-mining (or ML training) on up to 200 synthetic timeseries that have the same characteristic as ...

Ok, what you describe is creating a portfolio of profitable strategies. When uncorrelated, they even out each others ups and downs giving you a more smooth equity curve. I fully agree with you. However, would throwing together a bunch of edge-less ...

Sorry I misunderstood you. Yes, indeed. My goal was to show just that. However, the question remains how to differentiate lucky random strategies from strategies with an actual edge. Any thoughts?

The code is attached to post #1, so feel free to experiment with it yourself. You must have misinterpreted what that trader was doing, because it is not possible to predict random numbers. Neural nets are often initialized with random numbers before ...

The idea of a multi-currency test is that a valid strategy usually works on more than one market? Adding such a test would definitely raise the bar for random strategies and perhaps make it 10x harder for a random strategy to pass through. However, ...

Indeed. But that makes the challenge of finding a suitable strategy even harder! Now we can't even filter on good performance. Any slightly profitable random strategy could potentially be a good candidate for our portfolio Sorry, I don't ...