1 Topic by Vincenzo (edited by Vincenzo 2025-10-11 20:45:01)

  • Registered: 2024-02-23
  • Posts: 142

Topic: Follow-up: Effect of Filter Combinations and Post-Incubation Results

In the first part of this experiment (https://forexsb.com/forum/post/82865/#p82865),
I tested how different filter combinations applied to the same EA collection (233 EAs) affected Walk-Forward Analysis (WFA) success.

Results showed that filters alone could dramatically shift outcomes — from below 20 % to full 100 % WFA success.

To go further, I selected one setup — Combination A — with:

- Profit Factor > 1.1

- Winning Trades > 60 %

- SQN > 2

EAs meeting these rules were incubated on demo accounts and compared with older incubators created before SQN was used.
All results were manually collected last week from EAs running on Demo account across different symbols, timeframes, and brokers.

Results as Avg Win Rate (Profitable EAs / Total):

- Without SQN filter: 33 % (sample 348EAs)
- With SQN filter (Combination A): 55 % (sample 267EAs)

A total of 615 EAs were benchmarked.
Some SQN-filtered incubators reached over 70 % profitable EAs after incubation, while pre-SQN groups stayed around 25–40 %.

(Chart: EA Win Rate % After Incubation – SQN Filter vs No SQN)

Interpretation

The data suggest structural robustness over time.
Many EAs in this benchmark have been running for 300+ days, still active, trading, and trackable across multiple brokers.

Key points:

- Filter design strongly impacts long-term EA survival.
- SQN combined with PF and Win % clearly improves success probability.

Cross-broker, multi-timeframe behavior shows the effect isn’t dataset-specific.

Next Step

A practical approach might be:

- In the while several EAs have been moved from demos to live account and will be evaluated soon.

- Run 10 uncorrelated SQN-filtered EAs in one live portfolio. After ~50 trades per EA, switch off the weaker ones and add new SQN candidates to keep improving the portfolio’s overall win rate.

- I’ve also been copying only the trades from profitable SQN EAs on demo to live MT4, which helps reduce the usual performance drop when moving EAs from demo to real accounts.

Does an even better filter combination exist — one that can outperform this setup?

Let’s go back to testing and studying.

And above all, these results prove that the first part of the experiment was not just a dataset-driven bias, but a replicable effect visible across brokers, timeframes, and extended incubation periods.

Open to constructive observations...

Post's attachments

2025-10-09 ABS WinRate.png 55.47 kb, file has never been downloaded. 

You don't have the permssions to download the attachments of this post.

2 Reply by Blaiserboy (edited by Blaiserboy 2025-10-09 10:17:44)

  • Blaiserboy
  • Blaiserboy
  • Junior Part-Time Aspiring Space Cadet
  • Offline
  • From: Toronto
  • Registered: 2010-09-06
  • Posts: 2,869

Re: Follow-up: Effect of Filter Combinations and Post-Incubation Results

I think you will find Mt5 data includes varying spreads whereas Mt4 is constant spead, if spreads are material in your experimenting.

Also I think SQN requires 100 trades to be effective(Statistical Significance).

Blaiserboy's Website

  • Registered: 2024-02-23
  • Posts: 142

Re: Follow-up: Effect of Filter Combinations and Post-Incubation Results

That’s a very good hint, thanks.
I honestly hadn’t considered the difference in spread behavior between MT4 and MT5.
I’ve been gradually switching to MT5, but around 90 % of what I run is still on MT4.

Spread impact is already on my list for the next test matrix, but as you know, these things are resource- and time-intensive.
I prefer an incremental approach — too many variables at once can make interpreting the results much harder.

Have you already done any MT4 vs MT5 spread benchmark yourself?

  • Blaiserboy
  • Blaiserboy
  • Junior Part-Time Aspiring Space Cadet
  • Offline
  • From: Toronto
  • Registered: 2010-09-06
  • Posts: 2,869

Re: Follow-up: Effect of Filter Combinations and Post-Incubation Results

Sadly to say I have not done any great amount of testing.

Blaiserboy's Website

  • Blaiserboy
  • Blaiserboy
  • Junior Part-Time Aspiring Space Cadet
  • Offline
  • From: Toronto
  • Registered: 2010-09-06
  • Posts: 2,869

Re: Follow-up: Effect of Filter Combinations and Post-Incubation Results

Perhaps when you have arrived at the final testing technique you will share it, I notice that you have a very detailed method and use a lot of samples.

Blaiserboy's Website

  • Registered: 2024-02-23
  • Posts: 142

Re: Follow-up: Effect of Filter Combinations and Post-Incubation Results

of course, when data and results can support discussions here I will be back

  • Registered: 2024-02-23
  • Posts: 142

Re: Follow-up: Effect of Filter Combinations and Post-Incubation Results

Additional Notes on the Experiment Context

Just to clarify a few points for readers:

- The datasets, brokers, and starting periods were different — this was not same-data validation.

- The goal wasn’t to prove universal robustness, but to see how filter design affects selection success rate across independent demo incubations.

- All EAs had already passed Monte Carlo validation, so the test measured the marginal impact of filters, not basic robustness.

- Demo incubation is one gate in a multi-step pipeline (Generation → Monte Carlo → Incubation → Live).

- Combination A was predefined and applied both to past and new collections — part of an iterative workflow, not a backward fitting.

- Win rate check point included all EAs (winners + losers), avoiding survivorship bias.

- Cross-broker and multi-timeframe results confirm the effect isn’t dataset-specific.

In short, this experiment isolates how selection criteria influence long-term survival probability in demo validation. The final live journey is just started.

  • Popov
  • Popov
  • Lead Developer
  • Offline
  • From: Bulgaria
  • Registered: 2006-11-30
  • Posts: 8,270

Re: Follow-up: Effect of Filter Combinations and Post-Incubation Results

I temporarily banned Jurgen2100 for trolling.

Popov's Website

  • Blaiserboy
  • Blaiserboy
  • Junior Part-Time Aspiring Space Cadet
  • Offline
  • From: Toronto
  • Registered: 2010-09-06
  • Posts: 2,869

Re: Follow-up: Effect of Filter Combinations and Post-Incubation Results

The guys have to be allowed to express themselves without harassment, they are contributing and in this thread there may be something really useful if they are allowed to continue.

I, for one, am quite interested in this thread.

Blaiserboy's Website