Tickfloor

Do trading strategies work on ETFs?

None of the technical indicators and other rules passed the corrected test in these backtests. Of 366 strategies tested on ETFs, 70 finished ahead of the equal-weight benchmark on the point estimate, 18 of those with an unadjusted p-value under 0.05, and none met the corrected Benjamini-Hochberg bar (q below 0.10). The median strategy returned −3.8 pts/yr against the benchmark. These are results from our older test setup, which was built before our current testing rules. They have not been redone under those rules.

The universe is ETFs only, with data up to 15 March 2025. Technical analysis here means rules built from price and volume, such as moving averages, RSI and MACD; the technical indicators were tested alongside other rules, such as seasonality. Most strategies are published or popular rules coded from a source description (a few are Tickfloor research-desk hypotheses), charged modelled trading costs and scored against an equal-weight benchmark of the same assets.

The numbers

Research map: ETFs

Each family's size shows how many strategies we tested, and its colours show how each one did. Pick a family to open its page.

  • Edge excluded 64
  • Behind, not excluded 173
  • Behind, one good half 46
  • Too few trades 13
  • Ahead, not significant 70
Trend followingTrend following: Edge excluded, 6 strategies of 626Trend following: Behind, not excluded, 33 strategies of 6233Trend following: Behind, one good half, 2 strategies of 622Trend following: Too few trades, 3 strategies of 623Trend following: Ahead, not significant, 18 strategies of 6218MomentumMomentum: Edge excluded, 3 strategies of 56Momentum: Behind, not excluded, 28 strategies of 5628Momentum: Behind, one good half, 13 strategies of 5613Momentum: Ahead, not significant, 12 strategies of 5612VolatilityVolatility: Edge excluded, 5 strategies of 385Volatility: Behind, not excluded, 18 strategies of 3818Volatility: Behind, one good half, 8 strategies of 388Volatility: Too few trades, 2 strategies of 38Volatility: Ahead, not significant, 5 strategies of 385Mean reversionMean reversion: Edge excluded, 12 strategies of 3512Mean reversion: Behind, not excluded, 16 strategies of 3516Mean reversion: Behind, one good half, 2 strategies of 352Mean reversion: Too few trades, 1 strategy of 35Mean reversion: Ahead, not significant, 4 strategies of 354MacroMacro: Behind, not excluded, 17 strategies of 3417Macro: Behind, one good half, 5 strategies of 345Macro: Ahead, not significant, 12 strategies of 3412Day and month seasonali…Day and month seasonality: Edge excluded, 6 strategies of 306Day and month seasonality: Behind, not excluded, 13 strategies of 3013Day and month seasonality: Behind, one good half, 3 strategies of 303Day and month seasonality: Too few trades, 3 strategies of 303Day and month seasonality: Ahead, not significant, 5 strategies of 305Other tested patternsOther tested patterns: Edge excluded, 6 strategies of 276Other tested patterns: Behind, not excluded, 10 strategies of 2710Other tested patterns: Behind, one good half, 7 strategies of 277Other tested patterns: Too few trades, 1 strategy of 27Other tested patterns: Ahead, not significant, 3 strategies of 27Macro and…Macro and intermarket: Edge excluded, 3 strategies of 123Macro and intermarket: Behind, not excluded, 4 strategies of 124Macro and intermarket: Too few trades, 1 strategy of 12Macro and intermarket: Ahead, not significant, 4 strategies of 124Popular r…Popular rules, strongest version: Behind, not excluded, 6 strategies of 76Popular rules, strongest version: Ahead, not significant, 1 strategy of 7Managed f…Managed futures trend: Edge excluded, 4 strategies of 64Managed futures trend: Behind, not excluded, 1 strategy of 6Managed futures trend: Behind, one good half, 1 strategy of 6Social media chart patterns: Edge excluded, 5 strategies of 65Social media chart patterns: Behind, not excluded, 1 strategy of 6Pairs and stat arb: Edge excluded, 5 strategies of 55Rebalance control: Edge excluded, 2 strategies of 52Rebalance control: Behind, not excluded, 3 strategies of 53Sentimen…Sentiment extremes: Edge excluded, 1 strategy of 5Sentiment extremes: Behind, not excluded, 2 strategies of 52Sentiment extremes: Behind, one good half, 1 strategy of 5Sentiment extremes: Too few trades, 1 strategy of 5Calendar-event drift: Edge excluded, 3 strategies of 43Calendar-event drift: Behind, not excluded, 1 strategy of 4Oil shock attribution: Edge excluded, 1 strategy of 3Oil shock attribution: Behind, one good half, 1 strategy of 3Oil shock attribution: Ahead, not significant, 1 strategy of 3Rate decomposition: Behind, not excluded, 1 strategy of 3Rate decomposition: Ahead, not significant, 2 strategies of 32Capital deployment: Behind, not excluded, 1 strategy of 2Capital deployment: Behind, one good half, 1 strategy of 2Credit vol disagreement: Behind, not excluded, 2 strategies of 22Higher-timeframe cascade: Behind, not excluded, 2 strategies of 22Liquidity sweep: Behind, not excluded, 2 strategies of 22Macro disagreement: Behind, not excluded, 1 strategy of 21Macro disagreement: Behind, one good half, 1 strategy of 21Popular indicator rules: Behind, not excluded, 2 strategies of 22Volatility disagreement: Ahead, not significant, 2 strategies of 22Age price barrier: Edge excluded, 1 strategy of 1Alternative-data sentiment: Too few trades, 1 strategy of 1Breadth: Behind, not excluded, 1 strategy of 1Chart structure: Behind, not excluded, 1 strategy of 1Equity factors: Behind, one good half, 1 strategy of 1Excursion balance: Behind, not excluded, 1 strategy of 1Funding carry: Ahead, not significant, 1 strategy of 1Index alignment: Behind, not excluded, 1 strategy of 1Judas swing: Behind, not excluded, 1 strategy of 1Order block: Behind, not excluded, 1 strategy of 1Premium discount: Behind, not excluded, 1 strategy of 1Sequential evidence: Behind, not excluded, 1 strategy of 1Tail budget: Edge excluded, 1 strategy of 1Wealth mixture: Behind, not excluded, 1 strategy of 1

Historical backtests net of modelled costs, not a recommendation. A colour describes one strategy's result over its test window and says nothing about future returns.

The closest results

These five came out furthest ahead of the benchmark. Being furthest ahead among 366 tries is what luck alone produces, which is why the corrected q matters more than the headline figure.

Tickfloor's research desk has backtested 1,346 strategies, most against an equal-weight benchmark of the same assets rebalanced daily that pays no costs (the strategies pay theirs). After correcting for the 1,778 tests run, 0 passed. That does not prove no strategy works. These are results from our older test setup, which was built before our current testing rules. They have not been redone under those rules.

General information only. It doesn't consider your objectives, finances or needs. Tickfloor holds no financial services licence and never places trades.

Strategy families tested on ETFs

Do trading strategies work on ETFs?

None of the technical indicators and other rules passed the corrected test in these backtests. Of 366 strategies tested on ETFs, 70 finished ahead of the equal-weight benchmark on the point estimate, 18 of those with an unadjusted p-value under 0.05, and none met the corrected Benjamini-Hochberg bar (q below 0.10). The median strategy returned −3.8 pts/yr against the benchmark. These are results from our older test setup, which was built before our current testing rules. They have not been redone under those rules.

What is the benchmark?

An equal-weight long position in the same assets, rebalanced daily, with no trading costs taken off it. The strategies pay trading costs and the benchmark does not, which makes the test harder to pass, not easier.

Why correct the p-values?

When 1,778 tests are run, some will look significant by luck. The Benjamini-Hochberg correction accounts for how many were tried before calling any result real.

Is this advice on what to trade?

No. It reports what happened to published and popular rules in the past. General information only, not personal advice.

More

Next steps