Data & Methodology

Data as of 2026-08-13

This page discloses how every number we publish is produced. You need not believe our conclusions, but you should be able to reproduce our process under the same standard.

Backtest Window and Sample

Backtest Window and Sample
ItemSetting
Backtest window2023-01-01 to 2025-12-31
Bar intervalMainly 1-hour candles, 4-hour for some strategies
Instrument scopePerpetuals and spot for the top 20 by market cap
Data sourcePublic exchange candles (OHLCV), deduplicated with gaps in timestamps filled
Time zoneAll unified to UTC
The window covers one full cycle of decline, consolidation and advance. Pretty numbers produced only inside a one-way rally mean nothing, which is why we insist on spanning cycles.

Fill-Price Rule (the most critical one)

A signal is confirmed after the close of bar t, and the fill happens at the open of bar t+1.

Many backtests use the current bar's close as both the signal source and the fill price, which assumes you can transact at the instant of the close — the most common form of look-ahead bias, and it inflates returns significantly. Our engine forbids that pattern structurally.

If a backtest report does not state its fill-price rule, the return figures in that report cannot be assessed. This is the first question we suggest you ask about any strategy.

Cost Model

High-frequency strategies are extremely sensitive to costs: a strategy with 10 trades a day at 0.05% per side can incur annual trading costs of several times the principal. No backtest that excludes costs can serve as a basis for decisions.

Cost Model
Cost itemSettingNotes
Fees0.05% per sideCharged once on entry and once on exit
SlippageEstimated from instrument volatilityHigher values for less liquid instruments
Funding rateIncluded for perpetual strategiesSettled at historical actual rates
LatencyConservative assumptionNo fills assumed better than the t+1 open

Overfitting Controls

  • Walk-Forward rolling validation — tune on the training window, verify on the test window, roll forward, and count only out-of-sample performance
  • Parameter plateau check — good parameters form a plateau rather than an isolated spike; excessive sensitivity in the neighbourhood counts as overfitting
  • Parameter count constraint — more parameters fit noise more easily, so simpler structures come first
  • Trade count threshold — results with too few in-sample trades carry no statistical meaning
Every metric we publish is an out-of-sample result. In-sample numbers usually look better but are of no reference value to you.

Limits We Cannot Remove

  • Survivorship bias — the backtest universe is coins that still exist today, so samples that went to zero are inherently missing
  • Liquidity assumptions — real slippage on large size is higher than the model estimates
  • Regime change — trading rules, fee schedules and market structure change, and history need not repeat
  • Live-trading gap — live performance is usually below backtest, which is normal rather than anomalous
These limits cannot be removed with finer modelling. That is exactly why we repeatedly stress measuring the gap between live trading and backtest with small capital first. Historical backtest data does not constitute a promise of returns.

About the Sample Data

The market panels, signal lists and leaderboards on this site are sample data, used to show page structure and method. They are not real-time market data and not real user data. Once live data is connected, the data time and source will be clearly labelled.

Risk notice:Quantitative trading carries the risk of loss. All strategies, signals and performance figures on this site are historical backtest data and do not constitute a promise of returns, nor investment advice. Crypto markets are highly volatile, so validate with small capital first and comply with the laws of your jurisdiction.