Methodology notes
What a client of the standard review receives: methodology notes written on top of the Rigor report, with every figure taken from the report. It is an independent review: not an accounting or regulatory audit, and not investment advice.
Where the data comes from
The 11 series (10 portfolios and the market) are generated with seed 20261010: 240 months, from 2006-01 to 2025-12. No month is a real month.
Their parameters come from summary statistics of the “10 Portfolios Formed on Momentum” (value-weighted) and of the market and momentum factors of the Kenneth R. French Data Library, from 1963-01 to 2025-12, downloaded on 2026-10-10: each decile's alpha, market and momentum exposure and residual volatility, and the mean and volatility of the market and of momentum.
We neither store nor show that data: each file carries the notice “Copyright 2026 Eugene F. Fama and Kenneth R. French”, is built from the CRSP database, and the library's page gives no licence to copy or redistribute it. That is why this sample uses synthetic series with parameters taken from those statistics.
It is a simplification: the deciles' residuals are generated independent of each other, and the market's tails (a Student's t with 6 degrees of freedom) and the momentum crashes were chosen by hand; they do not come from those files.
What was reviewed
How it was measured
- With Rigor's engine unchanged, the same as for any report on the site: verdict policy 2026-09-27-dependence-1, seed 12345 and 500 bootstrap resamples.
- The variants' dates were compared with the series': they are unique, in order and the same.
- No public data downloaded: in the alpha the cash rate is taken as zero, and the report says so.
- The report uses its fund track record template (monthly returns someone presents to others): where it says “fund”, “manager” or “real history” it speaks of that template, not of the data, which in this sample is synthetic.
- Every figure carries its tag: Measured (computed on the series), Declared (stated by whoever supplies the data) or Not measured (could not be computed from what was supplied).
Results and what each one means
Class C: there is a material weakness; we would not rely on this fund's track record until it is resolved.
| Figure | Value | Evidence | What it means |
|---|---|---|---|
| Compound annual return | 13.3% | Measured | How much the series grew per year, compounded, from 2006-01 to 2025-12. |
| Annual volatility | 22.2% | Measured | How much the series moves in a typical year. |
| Annualised Sharpe | 0.68 | Measured | Mean return over its volatility, annualised, with no cash subtracted. |
| Maximum drawdown | -43.6% | Measured | The worst fall from an earlier peak. |
| Months under water | 35 | Measured | The longest stretch, in months, without regaining an earlier peak. |
| Probability that the true Sharpe is above zero (PSR) | 0.998 | Measured | As a single test, with the series' length, skew and tails. Passing needs 0.95 or more. |
| Deflated Sharpe (DSR) with 10 trials | 0.912 | Measured | The same probability, asking it to beat the best of 10 trials with no skill. With 0.95 or more it passes; between 0.5 and 0.95 it is weak. |
| Sharpe 10 trials with no skill would show | 0.36 | Measured | The best Sharpe to expect from pure luck among 10 trials with this length of history. |
| Years of history to leave that luck behind | 5.8 | Measured | With fewer years, a Sharpe like this one could come from picking the best of 10 trials. |
| Probability of overfitting (PBO, CSCV) | 25.7% | Measured | In what share of the data's splits the best variant in sample falls below the median out of sample. Above 50% is a bad sign. |
| Benchmark's compound annual return | 9.0% | Measured | The same measure for the market, over the same months. |
| Annual difference against the benchmark | +4.3% | Measured | The series' compound annual return minus the benchmark's. |
| Tracking error | 11.4% | Measured | How far the series strays from the benchmark in a typical year. |
| Information ratio | 0.45 | Measured | The mean annual excess over the benchmark (arithmetic mean, not the compound difference above) per unit of tracking error. |
The report's six questions
| Question | What it measures | Result |
|---|---|---|
| Statistical significance | Does the result stand out from chance as a single test? | Pass |
| Number of settings tried | Does it still stand after counting the attempts it came from? | Weak |
| Costs | Does it hold up against trading costs? | Not measured |
| Out of sample | Does it hold on data not used to choose it? | Not measured |
| Data quality and trading pattern | Does the data have gaps, jumps or suspicious patterns? | Pass |
| Benchmark | Does it add anything over holding the benchmark? | Weak |
Factor attribution
Rigor's engine splits the series' return against a single factor, the benchmark: how much the exposure to the market explains and how much is left as alpha.
| Figure | Value | Evidence | What it means |
|---|---|---|---|
| Beta against the benchmark | 1.25 | Measured | How much the series moves for each 1 % of the market. |
| Share of the return the exposure to the benchmark explains | 82.3% | Measured | What holding the market with that beta would give. With no cash rate, cash stays inside this exposure and the alpha. |
| Annual alpha | +2.7% | Measured | The return the exposure to the benchmark does not explain; its 95 % range runs from -2.8% to +8.1%. |
| Alpha's t-statistic | 0.96 | Measured | With t between -2 and 2, the alpha cannot be told apart from zero. |
Not measured Attribution to several factors (size, value, momentum and others): in the extended review, computed apart from the Rigor report with the methodology agreed in the quote. The engine does not compute it yet, so there are no figures here.
What is not measured
What a client would receive
- These notes, written on their own series.
- The full Rigor report, with all its sections.
- The PDF with the notes and the report.
- A 60-minute call and a re-run after 30 days.
Money reconciliation
We compare starting capital, known flows and net closed-trade P&L with the closing balance. A match does not authenticate the history.
The reconciliation could not be completed. No closed-trade list was supplied.
Gross − itemised costs = net closed-trade P&L: — − — = —
Starting capital + known flows + net P&L = expected closing balance: — + — + — = —
file units; currency not declared| Starting capital | — | Not measured |
|---|---|---|
| Flows after the start | — | Not measured |
| Gross closed-trade P&L | — | Not measured |
| Itemised costs | — | Not measured |
| Net closed-trade P&L | — | Not measured |
| Open-position value | — | Not measured |
| Expected closing balance | — | Not measured |
| Observed closing balance | — | Not measured |
| Difference (observed − expected) | — | Not measured |
| Tolerance | — | Not measured |
Executive summary
What this means for you
Statistical significance Pass
With this much data, a result like this is hard to get by pure luck. That says nothing about what happens next: only that the history is not noise.
Number of settings tried Weak
Part of the result may come from this being the best of several funds or strategies. You will be asked how many you run or have closed: declare it as the number of trials.
Costs Not measured
Without the list of trades the costs cannot be re-applied. Upload the platform report to measure them.
Out of sample Not measured
A fund's monthly record is its real history, but it does not say since when the manager has applied the same process, or whether any stretch is simulated. You will be asked for that date: declare it to measure it.
Data quality and trading pattern Pass
We found no jumps, gaps or hidden-risk patterns in the files. That does not rule out errors the files do not show.
Benchmark Weak
It beats the reference on return, but with more risk. Part of the difference may be extra risk only.
What to do now
If you show this fund to others, this is what they will ask you first on seeing this report, going by what the audit found.
What each class requires
The class does not measure how much was made, but how many questions your files answer. A better class does not mean the strategy will work.
- A
Statistics and number of trials pass; costs, out-of-sample and benchmark pass or do not apply; the data has no serious or warning flags.
- B
Statistics pass, the number of trials passes or was not declared and nothing fails, but costs, out-of-sample, benchmark, data quality or the number of trials still need measuring or strengthening.
- C
One dimension fails, or statistics or number of trials are weak.
Your report - D
The data or the statistics fail, or two dimensions or more fail.
Charts
Red flags found
No red flags in the audited files.
Plan to reach a better class
What the audit's rules would need to see in each open dimension, most decisive first. A better class means the files answer more questions, not that the strategy will work.
01 Declare how many funds you run Weak
DSR 0.912 at 10 trials; it passes at 0.95 or more and fails below 0.5. With 512 or more funds or strategies from the same manager it falls below 0.5.
- You will be asked how many funds or strategies you run or have closed: declare it as the number of trials, since one good record among many weighs less.
If this dimension passed and the rest stayed the same, the class would be B.
02 Compare with the fund's index Weak
Excess over the reference +659.7%. Drawdown 1.28 times the reference's; up to 1.0 times is accepted, that is, falling no further than it (not met).
- Check that the reference is your real alternative, over the same dates.
03 Confirm whether the figures are net of fees Not measured
A fund's monthly record already carries its trading costs inside each month, but without the list of trades they cannot be re-applied: the best possible class is B.
- You will be asked whether the figures are net of the management and performance fees: declare it and the report shows how much the fees weigh.
04 Declare since when your process is unchanged Not measured
The fund's record does not say since when the manager has applied the same process, or whether any stretch is simulated: without that date the best possible class is B.
- You will be asked since when the investment process has not changed and whether any stretch is simulated (pro forma): declare that date as the out-of-sample start and what follows is measured as unseen data.
Stress tests: without the best outcomes
We remove the best periods and trades from what you uploaded and measure what is left. If the total falls to zero or below, it rests on a few events that may not repeat. This is not a forecast.
How did it do in calm and in turbulent markets?
No split by the VIX: period returns do not establish an opening date or a within-period path. Not measured
What a fund investor would check
A fund factsheet's figures and two tests fund analysts use: whether the monthly returns are smoothed and whether months with a small loss are missing. It does not change the class: these are questions to ask.
No pattern No smoothing and no shortage of months with a small loss.
Compound annual return Measured
Annual volatility Measured
Positive months (240 months) Measured
Worst month (best: +19.7%) Measured
Deepest fall Measured
Months in a row below a previous high Measured
| Year | Jan | Feb | Mar | Apr | May | Jun | Jul | Aug | Sep | Oct | Nov | Dec | Full year |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2006 | +6.3% | +2.0% | +18.8% | -7.5% | +5.2% | +5.6% | -10.9% | +3.7% | -3.8% | +6.6% | +3.2% | -13.9% | +11.6% |
| 2007 | +12.8% | -7.4% | +0.8% | -1.2% | +4.5% | +1.5% | +5.0% | +6.5% | +9.0% | -8.4% | +2.4% | +4.4% | +31.6% |
| 2008 | +0.1% | -1.6% | -5.0% | -3.3% | +3.8% | -3.6% | +2.6% | +3.7% | +6.3% | -0.9% | -2.6% | -16.5% | -17.6% |
| 2009 | +10.2% | +0.6% | -4.9% | -3.3% | +1.3% | -3.9% | -0.1% | +6.3% | -12.0% | +0.3% | +1.0% | -3.2% | -8.9% |
| 2010 | +7.4% | +12.3% | +2.5% | +5.7% | +4.2% | +0.7% | +3.7% | -0.3% | -1.2% | +4.0% | -4.1% | +4.7% | +46.4% |
| 2011 | +1.7% | -11.2% | -4.1% | +6.6% | +1.0% | -4.4% | -12.8% | -2.8% | +3.0% | -2.2% | -10.9% | -5.7% | -36.1% |
| 2012 | -0.1% | +9.6% | -3.3% | +2.2% | -0.4% | -16.7% | +8.1% | -2.4% | +19.7% | +15.7% | -0.6% | +5.1% | +37.0% |
| 2013 | +3.9% | +1.0% | +11.4% | -2.1% | -5.7% | -2.7% | -5.2% | +1.9% | +12.8% | +3.8% | +2.2% | +3.6% | +25.6% |
| 2014 | +1.6% | -2.9% | +8.1% | +4.7% | -8.6% | -17.2% | +2.0% | -0.2% | -1.6% | +4.3% | +0.5% | +5.6% | -6.2% |
| 2015 | -0.8% | +1.8% | +4.3% | -4.7% | +1.0% | +7.2% | +0.6% | +0.7% | -4.1% | +12.0% | +3.3% | -0.2% | +21.8% |
| 2016 | +5.6% | -0.3% | -4.1% | -3.1% | -6.6% | +11.5% | +3.4% | +2.2% | +1.3% | +10.4% | +5.9% | +11.5% | +42.0% |
| 2017 | +3.4% | +6.0% | +4.0% | -5.5% | +4.6% | +3.2% | -1.5% | -1.2% | +7.1% | -2.1% | +6.6% | +6.1% | +34.0% |
| 2018 | +9.8% | +0.9% | -0.3% | +4.2% | -11.4% | -5.7% | +12.9% | -1.4% | +3.7% | -2.4% | -2.6% | -3.6% | +1.9% |
| 2019 | +8.8% | +0.9% | +6.0% | -2.7% | +3.0% | +4.4% | -2.7% | -1.2% | +6.5% | -6.1% | 0.0% | +1.3% | +18.5% |
| 2020 | +12.3% | +0.6% | -1.4% | 0.0% | -2.3% | +1.4% | +4.0% | -13.0% | +2.4% | +9.7% | -3.7% | +0.1% | +8.2% |
| 2021 | +6.6% | +9.2% | +2.3% | -7.1% | +3.1% | +1.7% | -0.8% | +7.7% | -2.2% | +0.4% | -4.6% | -1.4% | +14.2% |
| 2022 | -10.4% | -0.8% | -12.8% | +4.9% | +1.6% | -10.3% | -3.4% | +0.9% | -6.4% | +2.1% | +2.7% | +9.6% | -22.3% |
| 2023 | -10.5% | -2.2% | +8.4% | -2.2% | +3.6% | +14.3% | -17.3% | -0.1% | +6.7% | +3.3% | +0.3% | +7.1% | +7.6% |
| 2024 | -1.3% | +7.4% | +6.1% | +3.8% | -6.5% | -3.1% | +11.4% | +11.8% | +7.6% | +16.6% | +12.7% | +10.2% | +105.1% |
| 2025 | +0.8% | -3.7% | +2.7% | +2.6% | +8.3% | -4.9% | +3.1% | +0.3% | +3.8% | -0.2% | +4.3% | +5.4% | +24.0% |
Against its benchmark
From 2006-01 to 2025-12, 240 months shared with the benchmark file you uploaded. If the fund's figures are before fees, this comparison flatters it.
Ahead Ahead of its benchmark over the shared months, without tracking it like an index fund.
Annual difference against the benchmark (fund +13.3%, index +9.0%) Measured
Months it beat the benchmark Measured
Annual tracking error (information ratio 0.45) Measured
Beta to the benchmark (correlation 0.88) Measured
Up capture: share of the benchmark's rises it takes Measured
Down capture: share of the benchmark's falls it takes Measured
How much is cash, how much is the market and what is left?
Over 240 months shared with the benchmark, the fund's average yearly return splits into three parts that add up to the total. No cash rate covered those dates: cash is taken as zero, so the alpha also holds what cash would have paid.
| Part | A year |
|---|---|
| Cash (Treasury bills) | 0.0% |
| Exposure to the benchmark (beta 1.25 times the benchmark's return over cash) | +12.4% |
| What is left (alpha) | +2.7% |
| The fund's average return (arithmetic mean) | +15.1% |
Exposure to the benchmark explains 82% of the fund's return; cash is separate. Measured
Alpha a year: +2.7%, 95 % range -2.8% to +8.1% (t = 0.96). Measured With t between -2 and 2, the difference cannot be told apart from chance.
With this alpha and this noise, even 50 years of record would not be enough for the alpha to be two standard errors from zero. It is arithmetic, not a promise: it does not say the alpha exists or that it will continue.
The benchmark's returns as supplied; Rigor did not check them against the index.
How much would fees take?
The figures were not declared net of fees. This is the same history with the yearly fees an active fund commonly charges, taken out month by month. Measured
| Yearly fee | Yearly return | Total growth |
|---|---|---|
| No fee | +13.3% | +1124.7% |
| 1.0 % | +12.2% | +903.7% |
| 1.5 % | +11.7% | +809.3% |
| 2.0 % | +11.1% | +724.2% |
| 2.5 % | +10.6% | +647.4% |
| 2 % + 20 % of gains | +9.0% | +464.3% |
Single-percentage rows are the management fee only. The last row adds the classic performance fee: 20 % of each year's gain above the previous high.
At a fee of 3.9 % a year or more, the fund would have ended level with or below its benchmark over the months they share. Measured
How did it do in the known crises?
The fund's return through each market fall on the public record that its history covers in full (the market's peak to its trough). The dates are fixed: they are not fitted to the file. Measured
| Crisis | Fund | Index | Market over those months |
|---|---|---|---|
| 2008 financial crisis 2007-11 – 2009-02 | -2.3% | -3.3% | Nasdaq Composite -51.8% |
| Euro debt crisis 2011-05 – 2011-09 | -15.7% | -17.2% | Nasdaq Composite -15.9% |
| China and the oil fall 2015-06 – 2016-02 | +26.5% | +7.7% | Nasdaq Composite -10.1% |
| Late 2018 2018-10 – 2018-12 | -8.3% | -9.5% | S&P 500 -14.0% Nasdaq Composite -17.5% |
| Covid crash 2020-02 – 2020-03 | -0.8% | +0.9% | S&P 500 -19.9% Nasdaq Composite -15.8% |
| Inflation and rates, 2022 2022-01 – 2022-09 | -32.4% | -7.9% | S&P 500 -24.8% Nasdaq Composite -32.4% |
| Crypto winter 2022 2021-11 – 2022-12 | -26.9% | -3.6% | Bitcoin (Coinbase) -73.0% |
Market: the change from the close of the month before the window to the close of its last month, a fixed historical figure checked on 2026-09-25 against the index levels on FRED (Nasdaq Composite, S&P 500, Bitcoin (Coinbase)); no other data of these indices is read or shown. These are US equities and bitcoin: if the strategy trades another market (currencies, commodities, another country), take them only as context for what the market went through, not as its yardstick.
Worst 12 months in a row: -37.3%; best: +109.6%. 72% of the 12-month periods ended positive. Measured
Month-end returns as the file states them.
Resampled one-year risk
Maximum drawdown over one year · p50 Measured
Maximum drawdown over one year · p95 Measured
Maximum drawdown over one year · p99 Measured
| Probability of a fall of at least | In the simulations of the history |
|---|---|
| 10% | 63.55% Measured |
| 20% | 20.15% Measured |
| 30% | 4.60% Measured |
| 50% | 0.00% Measured |
Time in a row below the peak in the simulations, counted in months: median 5 Measured, in 1 of every 20 12 Measured
Is the file's worst fall normal for these returns?
Worst fall in the file: 43.6%. With the same returns in 1,000 random orders, the worst fall runs from 31.6% to 58.7% in 9 of 10 orders (median 42.1%). Measured
It is within the usual range for these returns: the order they came in makes it neither much milder nor much deeper.
Changing the order does not change the Sharpe, the volatility or the final result: it only shows the fall these returns usually bring over the whole file. It is not the one-year fall in the table above.
Assumptions:
- Resampled estimate from the supplied history: it is not a prediction.
- It assumes the future resembles the history; if the market changes, it no longer holds.
- A curve of daily closes does not show floating drawdown within the day.
What is left once luck is discounted?
The more configurations are tried, the higher the best one comes out even when none has an edge. Here the file's Sharpe sits next to what pure luck would give with the configurations counted, using the published math of Bailey and López de Prado and of Harvey and Liu. It is the same calculation that decides the "Number of settings tried" dimension, in numbers.
Beats luck, without margin The Sharpe of 0.68 beats the 0.36 that 10 settings with no skill would show, but not by the margin we ask: the confidence that it is not luck (DSR) is 91%, and passing this dimension needs 95%.
Sharpe 10 settings with no skill would show (the file's: 0.68) Measured
Years of history at which that luck falls below this Sharpe (the file has 20.0 years) Measured
Sharpe left after discounting 10 settings (Harvey and Liu) Measured
| Configurations tried | Sharpe luck would show | History needed | Is this history enough? |
|---|---|---|---|
| 10 | 0.36 | 5.8 years | yes |
| 100 | 0.59 | 15.0 years | yes |
| 1,000 | 0.75 | 24.7 years | no |
E[max Sharpe] of unskilled trials (Bailey & Lopez de Prado); minimum backtest length (Bailey, Borwein, Lopez de Prado & Zhu); Bonferroni haircut (Harvey & Liu).
What your clients will ask you
Whoever sees this report will ask this. For each question, what to provide to answer it.
- You will be asked: “Are the returns net of all fees (management, performance, entry and exit)? Which share class are they for?” Provide the fund's factsheet or prospectus, with its fees and share class.
- You will be asked: “Is the whole record the same fund, with the same manager and strategy, or does it include simulated years or another vehicle's?” Provide the fund's record since inception, with any simulated or other-vehicle stretch marked.
- You will be asked: “Does the manager run other funds or accounts with the same strategy, closed ones included?” Provide the records of the other funds or accounts with the same strategy, closed ones included.
- You will be asked: “Who calculates the net asset value and who audits the fund's accounts?” Provide the names of the fund's independent administrator and auditor.
Technical detail by dimension
| Dimension | Status | Reasons |
|---|---|---|
| Statistical significance | Pass | PSR 0.998 >= 0.95; bootstrap p5 Sharpe > 0 |
| Number of settings tried | Weak | DSR 0.912 between 0.5 and 0.95 with 10 trials counted in the files |
| Costs | Not measured | no trades uploaded; costs cannot be re-applied |
| Out of sample | Not measured | a fund's record does not say since when its process has run unchanged |
| Data quality and trading pattern | Pass | no red flags |
| Benchmark | Weak | excess return 659.74% > 0; drawdown deeper than the benchmark |
Thresholds applied: PSR to pass 0.95 · minimum PSR 0.8 · DSR to pass 0.95 · minimum DSR 0.5 · maximum PBO 0.5 · cost multiple it must withstand 3 · minimum out-of-sample Sharpe 0.5 · maximum out-of-sample Sharpe drop 1 · maximum drawdown versus the benchmark (times) 1
Annualised performance
| Metric | Value | Evidence | Note |
|---|---|---|---|
| Total return | 1,124.75% | Measured | |
| Compound annual return | 13.34% | Measured | |
| Annual volatility | 22.22% | Measured | |
| Sharpe | 0.6777 | Measured | |
| Sortino | 1.08 | Measured | |
| Maximum drawdown | -43.61% | Measured | |
| Win rate | — | Not measured | no trades uploaded |
| Trades | — | Not measured | no trades uploaded |
Statistical significance
| Metric | Value | Evidence | Note |
|---|---|---|---|
| Observations | 240 | Measured | |
| Sharpe per period | 0.1956 | Measured | |
| Skewness | -0.2200 | Measured | |
| Kurtosis | 3.60 | Measured | |
| Probabilistic Sharpe (PSR) | 99.83% | Measured | P[true Sharpe > 0] given length, skew and kurtosis |
| Minimum track record needed | 77 | Measured | observations needed for PSR to reach 0.95 |
| Observations missing | 0 | Measured |
Sharpe corrected for autocorrelation (Lo, 2002): it is not appreciably below 0.68, so the order of the returns does not inflate the plain Sharpe appreciably. When the correction raises it, the report does not use it, so as not to favour the file. Measured
The returns do not depend on each other appreciably: taking that into account does not change the probability that the true Sharpe is above zero. Measured
Multiplicity (number of trials)
Trials used in the deflated Sharpe: 10 Measured columns of the uploaded variants matrix
| Metric | Value | Evidence | Note |
|---|---|---|---|
| Trials used | 10 | Measured | columns of the uploaded variants matrix |
| Sharpe variance used | 0.0045 | Measured | |
| Sampling-error floor | 0.0045 | Measured | sampling variance of the Sharpe estimator |
| Variance increase from dependence | 1 | Measured | how many times the Sharpe's variance grows when the returns are not taken as independent (1 means no change) |
| Effective observations after dependence | 240 | Measured | |
| Observed across variants | 0.0025 | Measured | variance across 10 variants |
| DSR at the declared trials, which are the same as the trials used | 91.19% | Measured | PSR against E[max Sharpe] of 10 trials, columns of the uploaded variants matrix |
| Trials that bring DSR to 0.5 | 512 | Measured | smallest power-of-two trial count with DSR < 0.5 |
Variance used: the larger of the one observed across the variants you uploaded and the one sampling error produces.
| trials | Expected max Sharpe without skill | Deflated Sharpe (DSR) |
|---|---|---|
| 1 | 0 | 99.83% |
| 5 | 0.0797 | 95.86% |
| 10 | 0.1053 | 91.19% |
| 20 | 0.1271 | 84.76% |
| 100 | 0.1692 | 65.40% |
Stationary bootstrap (per period)
Stationary block bootstrap, resamples: 500 · block 20
| Estimate | p5 | p50 | p95 | |
|---|---|---|---|---|
| Sharpe per period | 0.1956 Measured | 0.0948 Measured | 0.1999 Measured | 0.3125 Measured |
| Total return | 1,124.75% Measured | 156.43% Measured | 1,212.18% Measured | 6,319.02% Measured |
Declared out-of-sample
Not measured a fund's record does not say since when its process has run unchanged
Trading costs
Periodic return series
For a series with a date and return, confirm the frequency and unit. Frequency, unit and gross/net labels are Declared; figures computed from the file are Measured.
- Series frequency
- Monthly Declared
- Return unit
- Fraction Declared
- Series used
- Return Declared
- Benchmark source
- Uploaded file Declared
- Periods per year
- 12 Declared
- Frequency confirmed in the form
- YesDeclared
- Unit confirmed in the form
- YesDeclared
- Benchmark periods per year
- 12 Declared
Sensitivity to the declared gross/net difference
The stress derives from the declared gross/net difference. It does not measure individual trading costs or reconstruct trades.
Cost reference: Gross return minus net return Declared
both gross and net period returns are required for cost stress Not measured
Supplied benchmark
| Metric | Value | Evidence | Note |
|---|---|---|---|
| Dates shared with the benchmark | 100.00% | Measured | |
| Observations | 240 | Measured | |
| Strategy total return | 1,124.75% | Measured | |
| Benchmark total return | 465.00% | Measured | |
| Return above the benchmark | 659.74% | Measured | |
| Strategy Sharpe | 0.6777 | Measured | |
| Benchmark Sharpe | 0.6367 | Measured | |
| Tracking error | 11.42% | Measured | |
| Information ratio | 0.4518 | Measured | |
| Strategy maximum drawdown | -43.61% | Measured | |
| Benchmark maximum drawdown | -33.95% | Measured | |
| Strategy drawdown versus the benchmark's (times) | 1.28 | Measured |
Combinatorially symmetric cross-validation (CSCV) overfitting
| Metric | Value | Evidence | Note |
|---|---|---|---|
| pbo | 25.71% | Measured | fraction of CSCV splits where the IS winner is below the OOS median |
partitions=8, combinations=70, parameter_variants=10, effective_variants=10, observations_used=240
Sub-periods (calendar years)
| Year | Return | Max drawdown |
|---|---|---|
| 2006 | 11.63% | -15.65% |
| 2007 | 31.64% | -8.40% |
| 2008 | -17.56% | -19.48% |
| 2009 | -8.88% | -17.84% |
| 2010 | 46.36% | -4.09% |
| 2011 | -36.15% | -37.19% |
| 2012 | 37.04% | -17.97% |
| 2013 | 25.64% | -14.86% |
| 2014 | -6.24% | -24.25% |
| 2015 | 21.75% | -4.71% |
| 2016 | 42.05% | -13.44% |
| 2017 | 34.01% | -5.48% |
| 2018 | 1.86% | -16.39% |
| 2019 | 18.51% | -6.09% |
| 2020 | 8.19% | -12.95% |
| 2021 | 14.18% | -7.77% |
| 2022 | -22.27% | -32.44% |
| 2023 | 7.61% | -17.36% |
| 2024 | 105.12% | -9.46% |
| 2025 | 24.03% | -4.93% |
Rolling windows
| Window | Min return | Min drawdown | Share negative |
|---|---|---|---|
| 3 | -22.72% | -24.25% | 34.87% |
| 6 | -28.32% | -28.32% | 33.62% |
| 12 | -37.27% | -37.27% | 27.95% |
Red flags
No red flags in the audited files.
Audited files (sha256)
| equity.csv | 25aed0a3d322b9107421fe1a89c362d40bdf35e5cde9aa8d1d34406920d119e4 |
| benchmark.csv | ced152424c17659de026602f925b8b6c5caff611b7e7fd5ff52700fae58f36c6 |
| variants.csv | 03ff8d176884bb630aa180724d951b9c33cbbde43feda55848c6a7a6a9f57ea7 |
| Dataset digest | 9a99ed7f5bb413e99aecfcc329ab68894aff4fad1598cbeddfea316a602969ed |
2006-01-31 → 2025-12-31 · monthly · 240 observations · return series
Declared by the client
| Metric | Value | Evidence | Note |
|---|---|---|---|
| Trials | 10 | Declared | |
| Cost per side (bps) | 0.00 | Not measured | default value, not declared |
| Out-of-sample start | — | Not measured | not declared |
| Benchmark applies | yes | Declared | |
| Initial balance | — | Not measured | not declared |
| Whose strategy it is | I'm the provider and show it to others | Declared |
No strategy description was written.
Not measured
- Declared out-of-sampleA fund's record does not say since when its process has run unchanged.
- Trading costsBoth gross and net period returns are required for cost stress.
Declared holdout seal
Not measured no out-of-sample start declared
sha256 of the audit JSONfc01eb63f47f5b7fb94378738b2607b90f3ff1066b6b3c9b2a5935cae31cfaaf