Audited builds

Each strategy below has been run on three years of real 1-hour market data across seven pairs, after fees and slippage, then audited for correctness and for uniform presentation in the Gunbot GUI. Every defect found was fixed, and every fix is documented with the measurement that proves it.

6strategies audited of 419
21issues found and fixed
7 × 3ymarkets × window, per strategy
53/53engine self-tests passing
StrategyMedian returnBuy & holdEdgeMax DDIn marketProfitableInvariantsUniformFixes
kalmanGridhand-written (no shared engine)0.3%39.2%-38.5%0.3%0.1%4 of 75 / 5 pass4 / 54DEFECTWARNINGDEFECTWARNING
meanRevOscillatorhand-written (no shared engine)6.1%39.2%-42.8%2.2%90.1%5 of 75 / 5 pass4 / 53DEFECTDEFECTWARNING
rangeRiderhand-written (no shared engine)4.3%39.2%-20.1%2.9%0.7%7 of 75 / 5 pass4 / 52DEFECTWARNING
volHarvesterhand-written (no shared engine)3.4%39.2%-34.6%1.4%99.5%7 of 75 / 5 pass4 / 54DEFECTDEFECTDEFECTWARNING
volRegimeMMhand-written (no shared engine)3.4%39.2%-34.6%1.4%99.5%7 of 75 / 5 pass4 / 54DEFECTDEFECTDEFECTWARNING
WaveTrend_LBdirectional1.1%39.2%-46.4%12.2%3.2%4 of 75 / 5 pass5 / 54DEFECTDEFECTDEFECTWARNING

Every figure is the median across the seven markets, not the best one. Ranking a strategy on its best pair measures which pair was picked, not what the strategy does.

How to read the return column

The edge column matters more than the return column, and both need the buy-and-hold column next to them. Over this window buy-and-hold was strongly positive on most pairs, so a strategy can show a respectable return while having badly underperformed simply holding the asset — and a strategy that sits in cash can show a small loss that would have looked like a large win in a bear window.

How every audit is measured — window, cost model, fill model and the five correctness invariants →

The reports

kalmanGridENGINEERING COMPLETE
Median 0.3% against buy-and-hold 39.2% over 7 markets × 3 years (2023-07-11 → 2026-09). 5 / 5 pass. 4 issues found and fixed.
quantroduction · spot · audited 2026-09-12
meanRevOscillatorENGINEERING COMPLETE
Median 6.1% against buy-and-hold 39.2% over 7 markets × 3 years (2023-07-11 → 2026-09). 5 / 5 pass. 3 issues found and fixed.
quantroduction · spot · audited 2026-09-12
rangeRiderENGINEERING COMPLETE
Median 4.3% against buy-and-hold 39.2% over 7 markets × 3 years (2023-07-11 → 2026-09). 5 / 5 pass. 2 issues found and fixed.
quantroduction · spot · audited 2026-09-12
volHarvesterENGINEERING COMPLETE
Median 3.4% against buy-and-hold 39.2% over 7 markets × 3 years (2023-07-11 → 2026-09). 5 / 5 pass. 4 issues found and fixed.
quantroduction · spot · audited 2026-09-12
volRegimeMMENGINEERING COMPLETE
Median 3.4% against buy-and-hold 39.2% over 7 markets × 3 years (2023-07-11 → 2026-09). 5 / 5 pass. 4 issues found and fixed.
quantroduction · spot · audited 2026-09-12
WaveTrend_LBENGINEERING COMPLETE
Median 1.1% against buy-and-hold 39.2% over 7 markets × 3 years (2023-07-11 → 2026-09). 5 / 5 pass. 4 issues found and fixed.
gunbot-quant · spot · audited 2026-09-12

What these reports do not claim

An audited strategy is correct, not profitable. Nothing here was measured on a live exchange, the engine models spot and long-only with a single price per bar, and no strategy in this pack should be run unattended on capital that matters.