Forecast Accuracy
Every forecast published on this site is written to an append-only ledger the moment it is generated, then scored against what actually happened once its 30-day horizon elapses. This page is that record.
What is being measured
We forecast a range with a probability, not a single number. So the question is not "was the price right" — it is calibration: when we say 80%, does it happen 80% of the time?
The central estimate deliberately sits close to the current price. Over a 30-day horizon a random walk is very hard to beat, and models that appear to beat it usually do so by extrapolating recent trends, which measurably increases error. We report our point error next to a random walk's so you can see we are matching it rather than claiming to beat it.
80% band coverage
54.9%
target 80.0%
50% band coverage
31.6%
target 50.0%
Median error
15.99%
random walk 15.70%
Resolved forecasts
942
1229 pending
Reliability
Forecasts grouped by the probability we stated. Perfect calibration means observed frequency equals stated probability in every bucket.
The white tick marks where the bar would end under perfect calibration.
By asset
| Asset | n | 80% band | 50% band | Med. error | vs walk | Brier |
|---|---|---|---|---|---|---|
| xrp | 23 | 4.3% | 4.3% | 25.18% | 24.60% | 1.311 |
| arbitrum | 23 | 8.7% | 8.7% | 47.44% | 47.04% | 1.079 |
| avalanche | 23 | 69.6% | 8.7% | 16.91% | 15.98% | 0.727 |
| bitcoin | 23 | 8.7% | 4.3% | 18.24% | 18.12% | 0.938 |
| bnb | 23 | 8.7% | 0.0% | 16.93% | 16.36% | 0.839 |
| aptos | 23 | 87.0% | 69.6% | 7.20% | 7.36% | 0.445 |
| cardano | 23 | 91.3% | 47.8% | 12.77% | 11.64% | 0.521 |
| chainlink | 23 | 26.1% | 4.3% | 26.15% | 25.83% | 0.887 |
| copper | 23 | 100.0% | 95.7% | 1.85% | 2.33% | 0.299 |
| corn | 23 | 34.8% | 8.7% | 11.46% | 11.45% | 1.102 |
| cosmos | 23 | 73.9% | 21.7% | 15.02% | 13.92% | 0.129 |
| dogecoin | 23 | 13.0% | 4.3% | 17.26% | 16.58% | 0.564 |
| ethereum | 23 | 13.0% | 8.7% | 23.53% | 23.57% | 0.883 |
| ethereum classic | 23 | 26.1% | 0.0% | 17.61% | 16.52% | 0.882 |
| filecoin | 23 | 69.6% | 30.4% | 14.65% | 13.73% | 0.666 |
| gold | 23 | 82.6% | 73.9% | 1.92% | 2.07% | 0.314 |
| hedera | 23 | 47.8% | 8.7% | 12.79% | 12.01% | 0.334 |
| injective | 23 | 52.2% | 34.8% | 22.57% | 23.14% | 0.768 |
| internet computer | 23 | 30.4% | 0.0% | 17.89% | 17.58% | 0.858 |
| litecoin | 23 | 21.7% | 0.0% | 15.97% | 15.65% | 0.934 |
| mantle | 23 | 13.0% | 0.0% | 28.16% | 26.58% | 0.866 |
| monero | 23 | 8.7% | 0.0% | 27.96% | 28.33% | 0.922 |
| naturalgas | 23 | 87.0% | 87.0% | 3.78% | 3.10% | 0.447 |
| near | 23 | 26.1% | 21.7% | 29.70% | 30.41% | 0.747 |
| oil | 23 | 87.0% | 65.2% | 12.08% | 12.84% | 0.344 |
| optimism | 23 | 78.3% | 26.1% | 14.19% | 12.46% | 0.495 |
| palladium | 23 | 100.0% | 91.3% | 2.04% | 2.03% | 0.296 |
| platinum | 23 | 100.0% | 82.6% | 4.19% | 4.43% | 0.166 |
| polkadot | 23 | 43.5% | 13.0% | 21.63% | 20.70% | 0.809 |
| render | 23 | 91.3% | 30.4% | 10.40% | 10.23% | 0.217 |
| shiba inu | 23 | 100.0% | 39.1% | 12.35% | 11.44% | 0.463 |
| silver | 23 | 100.0% | 78.3% | 3.40% | 3.88% | 0.115 |
| solana | 23 | 4.3% | 0.0% | 26.91% | 26.60% | 1.189 |
| stellar | 23 | 82.6% | 34.8% | 10.72% | 10.67% | 0.189 |
| sugar | 23 | 60.9% | 26.1% | 6.96% | 7.23% | 0.826 |
| sui | 23 | 82.6% | 43.5% | 9.81% | 9.22% | 0.485 |
| tezos | 23 | 43.5% | 21.7% | 20.69% | 19.24% | 0.677 |
| tron | 23 | 100.0% | 100.0% | 1.31% | 1.62% | 0.387 |
| uniswap | 23 | 8.7% | 0.0% | 42.25% | 42.49% | 1.082 |
| wheat | 23 | 78.3% | 30.4% | 9.51% | 9.74% | 0.858 |
| brent | 22 | 86.4% | 72.7% | 14.06% | 14.84% | 0.411 |
How to read this honestly
- Small samples mean little. A coverage figure over a handful of resolved forecasts is noise; treat anything under ~30 samples per asset as indicative only.
- Overlapping horizons are correlated. Consecutive daily forecasts share most of their 30-day window, so the effective sample size is well below the raw count.
- Good calibration in a calm market says little about a violent one. Volatility estimates lag regime changes, and the bands will be too narrow until they catch up.
- None of this makes any individual forecast reliable. A well-calibrated 70% is still wrong 30% of the time, and that is the point of publishing the number rather than a headline price.
Methodology and model details are on the methodology page. Forecasts are logged daily and scored automatically; nothing on this page is entered by hand.