Example robustness report: donchian-trades (entry=55, exit=15)

About this sample. Strategy: Donchian channel breakout (buy a close above the 55-day high, sell a close below the 15-day low), picked as the best of 20 combinations. This one is fed as a closed-trade list (21 trades) instead of an equity curve. The price data is a synthetic daily price series (a seeded random walk with bull, bear and choppy regimes, Jan 2018 to Dec 2025, 2,922 daily bars). It is not a real coin such as BTC. The parameters were tuned on the first 70% of the data (to Aug 6, 2023), then the report checks how the strategy held up on the untouched last 30%. Costs: 0.10% fee and 0.05% slippage per fill, long only. It's an example made with the Backtest Toolkit, not a forecast; with Toolkit Pro you can run the same kind of checks (out-of-sample split, Monte Carlo, parameter heatmaps) on your own data. ← All example reports (Backtest Toolkit)

start	2018-10-13
end	2025-12-31
total_return	+1169.1%
cagr	+42.2%
sharpe	0.82
sortino	3.60
max_drawdown	-32.4%
volatility	+62.4%

Summary

Likely overfit / luck

Robustness score out of 100. Input: donchian-trades.csv (trades, 21 rows, 2018-10-13 to 2025-12-31).

Check	Result	What it means
Out-of-sample degradation	fail	Sharpe 1.10 before 2023-08-07 vs 0.05 after (5% retained). Edges that survive usually keep at least half.
Year-by-year consistency	pass	5 of 8 calendar years were profitable.
Deflated Sharpe ratio	pass	Probability the true Sharpe is above zero: 100% before, 100% after deflating for 20 configuration(s) tried, skew 1.05 and kurtosis 2.9. Below 95% means the result is not distinguishable from the best of many lucky tries.
Monte Carlo	warn	2,000 resampled histories (trades). P(loss) 1%. Backtest max drawdown -32%, bad-case (p5) -59%. Plan for the bad case, not the backtest.
Parameter sensitivity	pass	20 parameter combos. 65% sit within 25% of the best sharpe (the 'plateau'); 100% are positive. A lone bright cell is a red flag; a broad plateau is reassuring.

Out-of-sample degradation

Sharpe 1.10 before 2023-08-07 vs 0.05 after (5% retained). Edges that survive usually keep at least half.

Year-by-year consistency

5 of 8 calendar years were profitable.

Deflated Sharpe ratio

Probability the true Sharpe is above zero: 100% before, 100% after deflating for 20 configuration(s) tried, skew 1.05 and kurtosis 2.9. Below 95% means the result is not distinguishable from the best of many lucky tries.

sr_period	0.4805
skew	1.0515
kurtosis	2.9373
n_obs	21
n_trials	20
sr_benchmark_period	0.0068
psr	0.9971
dsr	0.9967

Monte Carlo

2,000 resampled histories (trades). P(loss) 1%. Backtest max drawdown -32%, bad-case (p5) -59%. Plan for the bad case, not the backtest.

	total_return	cagr	max_drawdown
p5	77.4%	8.3%	-58.6%
p25	446.6%	26.5%	-44.3%
p50	1076.7%	40.7%	-34.6%
p75	2793.3%	59.4%	-26.2%
p95	10384.9%	90.5%	-15.4%

Parameter sensitivity

20 parameter combos. 65% sit within 25% of the best sharpe (the 'plateau'); 100% are positive. A lone bright cell is a red flag; a broad plateau is reassuring.

Method notes

OOS split: last 30% unless a split date is given. Monte Carlo: bootstrap of closed-trade returns (or stationary block bootstrap of per-bar returns for equity input). Deflated Sharpe: Bailey & Lopez de Prado (2014), benchmark = expected max Sharpe of N null trials. Parameter sensitivity requires the optimization grid CSV. Engine: Crypto Backtest Toolkit Pro.

Backtests are hypothetical, use historical or synthetic data, and do not guarantee future results. Not financial advice.