What we compare
For each city and fuel grade, we compare the forecast price with the price later reported for that date and convert the gap into cents per litre.
Model report card
How FuelRadar measures predictor accuracy
No public back-test sample is available yet. This report will populate after saved forecasts can be matched with later reported daily city averages.
Awaiting first back-test cycle
How we measure
Methodology in one screen
FuelRadar checks each forecast against the prices later reported for the same market and fuel grade.
Mean absolute error
Mean absolute error is the average size of those misses. It shows the typical cents-per-litre difference without letting high and low misses cancel each other out.
Window
Last 90 days only. The model recalibrates nightly, so older predictions reflect an earlier version and would skew the headline.
Minimum sample size
A city/fuel pair needs at least 3 back-test points to appear. Pairs with fewer data points are hidden rather than reported with a misleadingly small denominator.
Not enough back-test data yet
- The predictor needs at least three days of past predictions matched against actual prices before we publish a city in the back-test table. Check back tomorrow once the nightly job has had a chance to catch up.
Common questions
Predictor accuracy FAQ
Fuel prices move in small increments. A 2-cent miss is a different outcome from a 20-cent miss. MAE measures the magnitude of the error rather than a binary right-or-wrong result, making it a useful measure of typical forecast error.