# Time-series momentum backtest: 468 versions tested (2022–2025)

Source: https://backtestd.com/en/time-series-momentum-tested/  
Published 2026-10-26 · updated 2026-10-26 · Backtestd (Thomas Jamais)

## Does time-series momentum work?

No, not in our test. We coded the rule, tested 468 versions of it on 24 markets from 2022 to 2025, fees, slippage and funding included. 47% of the versions lost money. The best version did not survive older data it had never seen (2020–2022).

## Key facts

- **Versions tested**: 468
- **Markets**: 24
- **Period**: 2022-11-10 → 2025-07-09
- **Candles**: 1h
- **Costs**: fees, slippage and funding on every trade
- **Versions that lost money**: 47%
- **Verdict**: No edge after costs

## The rule people share

Go long after a coin rose over the last weeks, short after it fell.

## Why “the best version” misleads

With 468 versions, some look good by luck alone. The typical version made +0.003 R per trade; the best made +0.378. If the rule had no edge at all, the spread of results would look like this anyway: the best of many random tries always looks impressive. That is why we never trust the best version until it works on data it was not chosen on.

## Limitations

- A backtest is not live trading: fills, outages and your own discipline differ.
- We test the rule as written; a trader's discretion is not testable.
- Markets change. A rule that failed here could work elsewhere, and the reverse.
- Costs depend on your exchange and size; ours are typical retail perpetual-futures costs.

## Data (CSV, CC BY 4.0)

- Trades: https://backtestd.com/data/time-series-momentum-tested-trades.csv
- Every number: https://backtestd.com/data/time-series-momentum-tested.json
- Method: https://backtestd.com/en/method/

Cite as: Backtestd, "Time-series momentum backtest: 468 versions tested (2022–2025)", 2026-10-26, https://backtestd.com/en/time-series-momentum-tested/

_Educational content based on historical backtests. Not financial advice. Past results do not predict future results. Trading leveraged products can lose more than you invest._