Look-ahead bias

Look-ahead bias is using information in a test that was not available at the time of the simulated trade. It makes a rule look better than it could have been in real time.

How Look-ahead bias is calculated

Common causes: acting on a bar's close at that same bar's open, using a high or low before the bar ended, using revised company figures instead of the numbers first published, and using today's index membership for past dates. A guard is to compute every signal on closed bars and fill on the next bar.

How it is read

If a result looks too good, check the timing of every input first.

Common mistakes

• Using the close to decide and the same close to fill.
• Using a column in a data file that was filled in later, such as restated earnings.
• Smoothing with a centred window, which uses future bars.

What Tickfloor tested

Tickfloor has not published a backtest of a rule built only on Look-ahead bias. It describes or manages something rather than giving a signal, so there is no strategy to score. It still shapes how any tested rule should be read.

Lessons that cover it

• Why old test results can flatter a strategy
• Testing on prices the strategy never saw

Related concepts

• Backtest
• Survivorship bias
• Overfitting
• Out-of-sample testing
• All concepts

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

• See a full worked example (free, no account)
• Browse every course lesson by topic