Proof
We don't ask you to trust us.Here's the evidence.
Our signal detection is validated out-of-sample: on data the model was never tuned on, with real costs, through the tool's own exit. Below are the numbers as measured, with the limits in the same place.
FX majors · 5-minute · out-of-sample
Profit factor · +0.72 vs a plain rule-based core
A plain rule-core loses money on FX 5-minute. Our signal selection turns the same market positive from July 2025 onward, with real spreads (0.5 pip). Both years positive: 1.53 in 2025, 1.30 in 2026.
GBPUSD · USDJPY · USDCAD · NZDUSD · USDCHF
Indices · daily · seven-year holdout
Profit factor · +0.31 vs a break-even core
Dip-buy detection across 10 major indices, on a seven-year holdout (2015–2021) the rules were never fitted to. It lifts a break-even core. It was not profitable every year: 2018 and 2019 were down.
Long-only · through the tool's own exit
Every figure is the shipped combination: validated entries routed through PaceAlgo's own exit, measured out-of-sample with real costs. Not a research exit, and not a profit-factor promise.
Per pair · FX
The 1.43 isn't an averagehiding a dud.
Every FX pair on its own: profit factor, the plain rule-core it beats, trades and worst drawdown. Every pair clears its own losing baseline. The weakest is shown, not hidden.
Out-of-sample from July 2025, through the tool's own exit, 0.5-pip spread. Drawdown is the deepest fall of the running R-total from a high, at 1R risk per trade with no sizing.
How to read the table
01 · One R
Each trade risks one R: the distance from entry to stop. A stop costs −1R, a target pays more. No position sizing in any figure.
02 · Drawdown
The deepest the running R-total ever fell from a high before it recovered. The Max DD column shows it for each market.
03 · In practice
The pooled FX record fell 41.1R below its peak on its way to +256R net.
At a fixed 1% risk per trade, that is roughly a 41% equity dip. Real, and stated here rather than buried.
Forward track record
The real testruns forward.
Backtests show what survived validation. The forward record shows what happens next, published as it accrues and never curated after the fact. It is still an early sample: a receipt building in real time, not a long-run number yet.
449 trades. Every one public.
Losses included. Nothing backfilled. R values are gross.
As of 2026-10-19. Past performance does not predict future returns. Trading involves risk of loss. Not financial advice.
Verify it yourself
Every closed trade is posted the moment it closes in our public Discord, winners and losers, timestamped by Discord itself. Entries stay members-only: the public feed carries the outcome, not the tradeable signal.
Recompute the profit factor, win rate and drawdown yourself. Each row carries the stop and target the trade was given, so you can re-derive every R instead of taking ours on trust.
How to read the win rate. It counts how often a trade wins, not by how much. With the target further than the stop, half the trades can lose and the R-total still rises. That's why profit factor and cumulative R sit next to it.
Coverage
Exactly where the edge is,and where it isn't.
Most tools claim to work everywhere. That's the tell. Here is the honest map.
Signal detection validated out-of-sample, measured through the tool's own exit.
GBPUSD · USDJPY · USDCAD · NZDUSD · USDCHF and 10 major indices. No profit promise.
Everywhere else, PaceAlgo is a market-structure and regime tool, not an edge claim.
Clean levels, structure and risk, with no claim of a proven edge.
When the setup isn't there, it says so and stays quiet.
Most indicators only tell you when to trade. We also tell you when not to.
A number you can't reproduce isn't proof. So we show the method, the costs, and the years that didn't work.
Methodology
What these numbersactually mean.
The short version is below. For every term in plain English and how to reproduce the numbers yourself, see the methodology page.
Out-of-sample: the curve crosses the never-seen line and carries on in the same style.
Every result is counted in R, the distance to the stop, through the tool's own exit.
Identical in-sample, then the curve-fit line falls away on unseen data. The validated one carries on.
Out-of-sample
Measured on data the model never trained on and was never tuned against. In-sample numbers are excluded. They only show how well something memorised the past.
Walk-forward and holdout
FX signals come from a walk-forward model tested from July 2025 onward. The index rules are measured on a seven-year holdout (2015–2021) they were never fitted to. Fresh data, opened once.
Costs: net here, gross live
The out-of-sample figures are net: costs come off before the profit factor, FX at a 0.5-pip spread, indices at real per-trade costs. The live record is gross: its R values come from the indicator's own stop and target, without spread, slippage or commission. Expect the live profit factor to sit above the net figure.
The tool's own exit
Every figure runs through PaceAlgo's uniform exit, the one the tool runs live, not a more flattering research exit. What you see measured is what the tool does.
Why this isn't curve-fitting
Curve-fitting tests millions of combinations and keeps the best-looking one. It always backtests well and almost always fails live. We don't search for a flattering result: the figures are out-of-sample, cost-adjusted, framed as uplift over a plain core, with the losing years included.
Read this carefully
Honest limits.
What the numbers above do not say, in the same place as the claim.
- The tool uses a transparent, uniform exit, not the exact exit from our research validation. The numbers above are the shipped combination.
- On indices the strategy was not profitable every year: 2018 and 2019 were down. There is no profitable-every-year claim.
- The tool holds one position at a time, so overlapping signals aren't all taken: about 56% on FX and 68% on indices are skipped. The profit factor applies to the trades actually taken.
- Backtests are descriptive, not a promise. Past performance does not predict future results, and live results vary by broker, feed, spread and execution.
- The edge is validated on specific markets and timeframes. Everywhere else PaceAlgo is an analysis layer, not an edge claim. Trading involves substantial risk of loss. Nothing here is financial advice.
Watch it work in the open.
That is the whole record, wins and losses, updated as trades close.