Forecast Accuracy
We track every AI forecast against actual market outcomes. No cherry-picking — every prediction made 4+ weeks ago is measured here.
Forecasts Tracked
0
Avg Price Error
0.0%
lower is better
Trend Accuracy
0.0%
rising / stable / softening correct
Accuracy data is building up. Check back after forecasts have been running for 4+ weeks.
How We Measure Accuracy
Every forecast is logged with a timestamp and a predicted price for a specific vehicle segment. Once 4 weeks have elapsed, we look up the actual market median price (from live dealer inventory) that was recorded after the forecast date.
Average Error % measures how far off the predicted price was from the actual median: |predicted − actual| / actual × 100. Lower is better. Used car markets are inherently noisy, so errors under 5% are considered strong performance.
Trend-Classification Accuracy measures whether the directional call matched actual price movement: a Rising classification is correct if the price actually rose; a Softening classification is correct if it fell; a Stable classification is counted as correct when prices stayed roughly flat.
We do not cherry-pick results. Every forecast in our database is included once it has a corresponding actual price to compare against.
See these numbers move — get the weekly recap
Every Sunday: how each segment moved, which forecasts landed, and what the macro data is signaling.
Free. One email per week. Unsubscribe in one click.
Frequently Asked Questions
How accurate are CarCast's used car price forecasts?▾
CarCast measures accuracy by comparing every forecast made 4+ weeks ago against actual market prices recorded after the forecast date. We publish average % error and trend-classification (rising/stable/softening) accuracy transparently on this page.
What does 'trend-classification accuracy' mean?▾
Trend-classification accuracy measures how often our directional calls matched actual price movement: Rising classifications should correlate with prices that actually rose, Softening with prices that fell. A Stable classification is counted as correct when prices stayed roughly flat.
How often are accuracy stats updated?▾
Accuracy stats are computed in real time from our live database each time you load this page. New forecasts are added to the accuracy pool once they are at least 4 weeks old.
Which vehicle segments are tracked?▾
CarCast tracks 1138 vehicle segments spanning trucks, SUVs, EVs, sedans, and classic models. Each segment has its own accuracy breakdown on this page.