| Audited system | temoin-sain |
| Engine version | 1.0.0 |
| Method version | 1.0 |
| Seed | 0 |
| SHA-256 fingerprint of the data | d4f73aca2abb4c9fc7d98e36556914619a30fd503e57dbe4ac6471c2fb446d5f |
| Monte Carlo iterations | 10 000 |
| Number of trials used (N) | 10 |
| Period covered | 2021-01-11T16:40:28 → 2024-02-24T04:29:18 |
| Usable / supplied trades | 600 / 600 |
| Currency | USD |
| Initial balance | 10 000.00 |
| Service | Audit complet (audit_complet) |
Verdict: GO.
Findings: 0 blocking, 0 major, 0 minor, 6 informational.
Green light. The results provided passed all five statistical tests and no serious flaw was found in the way the trading is done. This means the observed performance is neither explained by chance, nor carried by a few lucky trades, nor manufactured by questionable data — over the period and data provided.
The verdict covers only what was given to the auditor: the closed trades in the file, over the period covered. It rests on no human judgement and no overall score: every test has a threshold fixed in advance by the method, and the verdict follows mechanically from those thresholds. The same file, audited again tomorrow with the same version, yields exactly the same report.
The five questions put to the results, and the numeric answer for this file:
When several versions of a strategy are tried before one is kept, the best one always looks good, even if none has an edge. This test computes the probability that the performance is real once that effect is corrected, for 10 declared variant(s): 97.6 %. Pass threshold: 50.0 %. Test passed.
The profit factor is the total won divided by the total lost (1.00 = break-even). The same trades were replayed 10 000 times in a different order, in blocks, to see what the same strategy would yield with less luck: in the 5 % least favourable scenarios the profit factor falls to 1.187. Threshold: 1.00 — below it, the strategy loses money in those scenarios. Test passed.
The drawdown is the largest fall between a peak and the trough that follows it. The observed one (2 042.87) is larger than in 78.1 % of random reorderings of the same trades. A very low value (under 5 %) would signal a curve too smooth to be honest; a very high value means the losses came clustered, which is harder to live through than the final result suggests. Test passed.
10 000 systems with no edge at all, but winning and losing amounts of the same size as this one, were simulated; 0.0 % of them did as well or better. Threshold: 5.0 % — above it, this system cannot be told apart from a system with no edge. Test passed.
A strategy tuned on one period tends to shine there and disappoint afterwards. This test compares its performance on periods not used for tuning: it keeps 65.4 % of it. Threshold: 40.0 %. Test passed.
No serious flaw was found in the way the trading is done: no martingale, no grid, no abnormal concentration of profit, no sign of tampered data.
What remains true despite the green light: a statistical test measures the past that was provided, not the future. The drawdown figures in the “Benchmarks” section show the size of temporary losses it is reasonable to expect from this system as it was observed.
This report states facts; it recommends no settings and predicts nothing.
The verdict follows mechanically from the barriers below; no composite score.
| Barrier | Value | NO-GO threshold | Indecision band | Status |
|---|---|---|---|---|
| Deflated Sharpe ratio (DSR) | 0.976 | < 0.500 | [0.450 ; 0.550] | passed |
| Profit factor, 5th percentile of the block bootstrap | 1.187 | < 1.000 | [0.950 ; 1.050] | passed |
| Percentile of the observed drawdown among order permutations | 78.140 | < 5.000 | [3.000 ; 8.000] | passed |
| p-value against the no-edge null | 0.000 | ≥ 0.050 | [0.030 ; 0.080] | passed |
| Out-of-sample walk-forward efficiency | 0.654 | < 0.400 | [0.350 ; 0.500] | passed |
No finding at this level.
Variance of Sharpe ratios across variants unknown: Lo approximation (V = 0.0017) for N = 10 trials. Conservative correction: the true DSR is probably lower.
Detector “execution_realism” not run: no price series provided.
Detector “lookahead” not run: no price series provided.
Fields absent from the source: commission, swap. Analyses that depend on them are disabled and reported as such.
The “no-edge” null keeps the empirical distributions of gains and losses and only neutralises their frequency (p₀ = 0.3832). It answers: “is the observed hit rate explainable by luck, given this gain/loss profile?” — it is not an efficient-market null.
Detector “stop_geometry” not run: no price series provided.
PSR: probability that the true Sharpe is positive, corrected for skewness and fat tails. DSR: the same probability evaluated against the best Sharpe expected by chance after N trials.
| Probabilistic Sharpe ratio (PSR) | 0.9998 |
| Deflated Sharpe ratio (DSR) | 0.9760 |
| Expected maximum Sharpe under the null (SR₀) | 0.0646 |
| Number of trials used (N) | 10 |
| Variance of Sharpe ratios across variants (V) | 0.001684 |
| Source of V | Lo approximation (conservative: the true DSR is probably lower) |
This system stays significant up to at least 1 000 tested variants (grid bound).
| N trials | DSR |
|---|---|
| 1 | 0.9998 |
| 10 | 0.9760 |
| 50 | 0.8942 |
| 100 | 0.8377 |
| 300 | 0.7279 |
| 1 000 | 0.5923 |
Three simulations, three questions: the bootstrap measures how unlucky the same edge can get; the permutation tests whether performance owes to trade order; the null counts edge-less systems that would do as well.
The “no-edge” null keeps the empirical distributions of gains and losses and only neutralises their frequency (p₀ = 0.3832). It answers: “is the observed hit rate explainable by luck, given this gain/loss profile?” — it is not an efficient-market null.
| Bootstrap method | stationary blocks (Politis-Romano), automatic length |
| Mean block length | 1.00 |
| Profit factor p05 / p50 / p95 | 1.187 / 1.378 / 1.596 |
| Net profit p05 / p50 / p95 | 6 679.99 / 12 692.53 / 18 690.96 |
| Drawdown p50 / p95 / p99 | 1 706.73 / 2 897.87 / 3 678.94 |
| Observed drawdown | 2 042.87 |
| Percentile of the observed drawdown among permutations | 78.1 |
| Permutation drawdown p50 / p95 | 1 670.50 / 2 608.53 |
| Equilibrium hit rate p₀ | 38.3 % |
| p-value (net profit ≥ observed) | 0.0005 |
| Net profit of null systems p50 / p95 | -103.24 / 5 835.66 |
Classifier used: volatility terciles (rolling standard deviation of P&L, no prices); unclassified trades: 2.
| Regime | Trades | Net profit | PF | Hit rate | Share of net |
|---|---|---|---|---|---|
| low volatility | 200 | 6 002.33 | 1.523 | 47.0 % | 47.1 % |
| medium volatility | 199 | 2 065.67 | 1.188 | 44.2 % | 16.2 % |
| high volatility | 199 | 4 849.49 | 1.446 | 47.7 % | 38.0 % |
| Quarter | Trades | Net profit | PF |
|---|---|---|---|
| 2021-Q1 | 31 | 1 840.05 | 2.473 |
| 2021-Q2 | 52 | 1 132.66 | 1.399 |
| 2021-Q3 | 47 | 1 388.94 | 1.605 |
| 2021-Q4 | 49 | 826.58 | 1.275 |
| 2022-Q1 | 51 | -1 007.03 | 0.712 |
| 2022-Q2 | 48 | 2 181.53 | 1.880 |
| 2022-Q3 | 45 | 1 269.35 | 1.569 |
| 2022-Q4 | 62 | 1 066.97 | 1.331 |
| 2023-Q1 | 49 | 684.72 | 1.234 |
| 2023-Q2 | 38 | -647.49 | 0.754 |
| 2023-Q3 | 60 | 1 302.22 | 1.350 |
| 2023-Q4 | 42 | 1 886.74 | 1.931 |
| 2024-Q1 | 26 | 826.17 | 1.579 |
Statistical drawdown markers from the block bootstrap, to compare with the live drawdown. They are not strategy settings.
| Observed maximum drawdown | 2 042.87 |
| Bootstrap drawdown, 95th percentile | 2 897.87 |
| Bootstrap drawdown, 99th percentile | 3 678.94 |
No condition.
qaudit 1.0.0 — method 1.0 — schema 1.0 — seed 0 — fingerprint d4f73aca2abb4c9fc7d98e36556914619a30fd503e57dbe4ac6471c2fb446d5f — service audit_complet.
Reproducible: same inputs + same version + same seed = same report, byte for byte.