Methodology
How we validate — and how you check it.
The proof page shows the numbers. This page shows how they were measured, defines every term behind them in plain English, and points you at the raw data so you can reproduce them yourself. If a method can't survive being explained, it isn't one.
A number you can't reproduce isn't proof. So everything below is designed to be checked — the method, the costs, and the years that didn't work.
01 — Train forward, test once
The validation pipeline
The whole method fits in one picture. Train on a window that's frozen the moment testing starts; run forward onto data the model never saw; measure once. Nothing gets refitted after it's opened.
1 · Train (frozen)
The model learns on a fixed historical window. Once testing begins, that window is frozen — no going back to adjust it after seeing how the test turned out.
2 · Walk forward
It's then run on the data that comes next in time — the out-of-sample slice — exactly as it would trade live, with no knowledge of what happens after each bar.
3 · Measure once
The result is read a single time, after costs, through the shipped exit. First look, only look. That single number is what we publish.
02 — No jargon left unexplained
Every term, plainly
The words behind the numbers, in plain English — with the reason each choice is the honest one, not just what it means.
Out-of-sample
The results are measured on price data the model had never seen and was never tuned against — a separate slice of history, held back on purpose.
Why it's honest · An in-sample number only tells you how well something memorised the past. It always looks good and almost never survives contact with the future. Out-of-sample is the only test that means anything.
Walk-forward
We train on a fixed window, then test on the data that comes immediately after it — moving forward through time, the way you'd actually trade, never letting the future leak into the training.
Why it's honest · It mirrors reality: you can only ever trade on what's already happened. Walk-forward stops the classic cheat of quietly using tomorrow's data to explain today.
Holdout
For the index rules, a full seven-year block (2015–2021) was set aside and opened exactly once, at the end, to measure — never to tune.
Why it's honest · Opened once means we couldn't peek, adjust, and re-test until it looked good. The first look is the only look — that's what makes the number trustworthy.
After costs
Transaction costs are subtracted before any profit factor is reported — FX at a 0.5-pip spread, indices at real per-trade costs. Every figure we publish is net, not gross.
Why it's honest · Gross numbers are a marketing trick. Costs are where a lot of paper edges quietly die, so we take them out first and show you what's actually left.
Through the tool's own exit
The published numbers use the exact stop, target and trailing logic the indicator runs live — not a separate, more flattering research exit.
Why it's honest · It would be easy to validate one exit and ship another. We measure the shipped combination, so what you see tested is what the tool actually does on your chart.
One position at a time
The tool holds a single trade at once, so overlapping signals aren't all taken (FX ~56%, indices ~68% of detected signals go untraded). The profit factor applies to the subset actually traded.
Why it's honest · It's the honest constraint of how a person trades one account. We report the number on what you could really have taken, not an idealised parallel-universe portfolio.
Profit factor
Gross dollars won divided by gross dollars lost. Above 1.0 means the strategy made money after costs; 1.43 means $1.43 came back for every $1.00 risked and lost.
Why it's honest · It's harder to game than win rate — a tool can win 70% of the time and still lose money if the losses are big. Profit factor captures the whole picture in one number.
R (risk-multiple)
One R is the amount you risked on a trade — the distance from entry to stop. A +2R win makes twice what you risked; a −1R loss is a full stop-out. Results are counted in R, not dollars.
Why it's honest · R makes every trade comparable regardless of account size or position size, and it's how the payoff distribution is actually built. It's the unit that survives translation to your account.
Win rate
The percentage of trades that close in profit. Useful context — but on its own it says nothing about whether a strategy makes money.
Why it's honest · A high win rate with a poor risk-reward loses; a low win rate with big winners wins. That's why we lead with profit factor, not win rate.
Want the long version on win rate specifically? Read why win rate is a vanity metric →
03 — The failure mode we avoid
Why this isn't curve-fitting
Curve-fitting is what happens when you test millions of parameter combinations and keep the one that looks best on history. In-sample, a curve-fit line and a validated line look identical. Out-of-sample — past the divider — the fitted one falls apart while the validated one holds.
How we stay on the right side of that line
We don't search for a flattering result. The figures we publish are out-of-sample, cost-adjusted, framed as the uplift over a plain rule-based core, and reported with the losing years included. A backtest that's been optimised until it sparkles is a warning sign, not a selling point — and it's exactly the thing this method is built to expose.
04 — Honesty is also about limits
What we don't claim
A method is only as honest as what it refuses to say. Here's what you will never hear from us.
We don't claim a fixed future profit factor. The numbers are descriptive of a measured period, not a promise about the next one.
We don't claim it works on every market. The edge is validated on FX majors (5-minute) and ten major indices (daily). Everywhere else PaceAlgo is an honest structure-and-regime tool — not an edge claim.
We don't claim it's profitable every year. On indices, 2018 and 2019 were down. We state that in the same place as the headline, not in a footnote.
We don't market the research exit. We only publish the shipped tool-exit, because that's what you actually run.
We don't promise you'll match the backtest. Live results vary by broker, feed, spread and execution — and past performance is not indicative of future results.
05 — Don't trust us. Check us.
Verify it yourself
Everything above is only worth something if you can test it without our permission. Three ways to do exactly that:
Recompute the raw data
Every closed forward trade is downloadable as a CSV — date, symbol, side, module, entry, exit, outcome and R. Load it into a spreadsheet and recompute the profit factor, win rate and drawdown yourself.
Download the trade log →Watch it accrue live
Every signal is posted the moment it closes in the public Discord — winners and losers, timestamped by Discord itself, never backfilled. Watch the forward record build in real time.
Open the Discord →Read the numbers in context
The proof page carries every figure with its sample size, its baseline, and the losing years stated alongside — nothing buried in a footnote.
See the proof →New to trading and not sure what half of this means yet? Start with the plain-English walkthrough.
Start here