Accuracy
How accurate is the Otherdeed for Otherside model?
Every score comes from the newest chronological hold-out; the target sale is excluded from training, comparables, and its causal floor proxy.
Median accuracy (100−APE)
92.8%
Mean accuracy (100−APE)
86.0%
Within ±5%
42%
Within ±10%
58%
Within ±20%
79%
Bias
-1.1%
Accuracy by market tier
Floor, middle-market, and grail sales are scored separately so aggregate accuracy cannot hide a weak segment
| Tier | Sales | Median accuracy | Within ±10% | Bias |
|---|---|---|---|---|
| floor | 1695 | 94.1% | 62% | -1.9% |
| middle | 66 | 61.3% | 12% | -4.3% |
| grail | 300 | 86.8% | 42% | +4.3% |
Weekly median accuracy
Chronological hold-out accuracy by sale week
Error distribution
Signed hold-out error; positive means over-predicted
Scored hold-out sales
60 out-of-sample predictions frozen at evaluation time
| Item | Tier / evidence | Date | Sale | Model | Error | Accuracy |
|---|---|---|---|---|---|---|
| #46459 | floor · high | Nov 2, 2026 | 0.063Ξ | 0.067Ξ | +7.2% | 92.8% |
| #21386 | floor · high | Nov 2, 2026 | 0.068Ξ | 0.064Ξ | -5.2% | 94.8% |
| #78415 | floor · high | Nov 2, 2026 | 0.062Ξ | 0.071Ξ | +14.5% | 85.5% |
| #21386 | floor · high | Nov 2, 2026 | 0.062Ξ | 0.065Ξ | +4.3% | 95.7% |
| #71108 | floor · high | Nov 2, 2026 | 0.120Ξ | 0.065Ξ | -45.8% | 54.2% |
| #56350 | floor · high | Nov 2, 2026 | 0.068Ξ | 0.066Ξ | -2.9% | 97.1% |
| #23162 | floor · high | Nov 2, 2026 | 0.065Ξ | 0.067Ξ | +2.8% | 97.2% |
| #98306 | floor · high | Nov 1, 2026 | 0.067Ξ | 0.059Ξ | -12.0% | 88.0% |
| #83505 | floor · high | Oct 31, 2026 | 0.067Ξ | 0.059Ξ | -12.1% | 88.0% |
| #21386 | floor · high | Oct 30, 2026 | 0.063Ξ | 0.061Ξ | -3.0% | 97.0% |
| #48816 | floor · high | Oct 30, 2026 | 0.062Ξ | 0.070Ξ | +13.5% | 86.6% |
| #32954 | grail · low | Oct 30, 2026 | 0.700Ξ | 0.384Ξ | -45.1% | 54.9% |
| #1553 | grail · low | Oct 29, 2026 | 0.625Ξ | 0.494Ξ | -21.0% | 79.0% |
| #23522 | floor · high | Oct 29, 2026 | 0.063Ξ | 0.065Ξ | +3.3% | 96.7% |
| #78108 | grail · high | Oct 29, 2026 | 0.061Ξ | 0.061Ξ | +0.6% | 99.4% |
| #53452 | floor · high | Oct 29, 2026 | 0.063Ξ | 0.059Ξ | -6.2% | 93.8% |
| #49529 | floor · high | Oct 29, 2026 | 0.063Ξ | 0.059Ξ | -6.2% | 93.8% |
| #99328 | grail · high | Oct 29, 2026 | 0.061Ξ | 0.060Ξ | -1.0% | 99.0% |
| #95364 | grail · high | Oct 29, 2026 | 0.061Ξ | 0.062Ξ | +2.3% | 97.7% |
| #561 | floor · high | Oct 29, 2026 | 0.232Ξ | 0.078Ξ | -66.4% | 33.6% |
| #78108 | grail · high | Oct 29, 2026 | 0.058Ξ | 0.068Ξ | +18.1% | 81.9% |
| #95536 | grail · high | Oct 28, 2026 | 0.273Ξ | 0.189Ξ | -30.7% | 69.3% |
| #26647 | grail · high | Oct 28, 2026 | 0.222Ξ | 0.105Ξ | -52.7% | 47.3% |
| #95536 | floor · high | Oct 27, 2026 | 0.190Ξ | 0.067Ξ | -64.7% | 35.3% |
| #99328 | grail · high | Oct 27, 2026 | 0.058Ξ | 0.068Ξ | +18.1% | 81.9% |
| #4500 | middle · low | Oct 27, 2026 | 0.124Ξ | 0.125Ξ | +0.8% | 99.2% |
| #23522 | floor · high | Oct 27, 2026 | 0.058Ξ | 0.078Ξ | +34.0% | 66.0% |
| #53166 | floor · high | Oct 27, 2026 | 0.063Ξ | 0.076Ξ | +20.6% | 79.4% |
| #58943 | floor · high | Oct 27, 2026 | 0.061Ξ | 0.074Ξ | +20.3% | 79.7% |
| #26648 | floor · high | Oct 27, 2026 | 0.074Ξ | 0.060Ξ | -19.0% | 81.0% |
| #21386 | floor · high | Oct 26, 2026 | 0.058Ξ | 0.068Ξ | +18.3% | 81.7% |
| #3310 | floor · high | Oct 26, 2026 | 0.139Ξ | 0.075Ξ | -46.1% | 53.9% |
| #4766 | middle · high | Oct 26, 2026 | 0.200Ξ | 0.098Ξ | -51.0% | 49.0% |
| #614 | floor · high | Oct 26, 2026 | 0.252Ξ | 0.088Ξ | -65.1% | 34.9% |
| #27143 | floor · high | Oct 26, 2026 | 0.060Ξ | 0.062Ξ | +3.3% | 96.7% |
| #84200 | floor · high | Oct 26, 2026 | 0.060Ξ | 0.064Ξ | +6.7% | 93.3% |
| #96934 | floor · high | Oct 26, 2026 | 0.060Ξ | 0.060Ξ | 0.0% | 100.0% |
| #99514 | floor · high | Oct 26, 2026 | 0.060Ξ | 0.062Ξ | +3.3% | 96.7% |
| #88811 | floor · high | Oct 26, 2026 | 0.060Ξ | 0.072Ξ | +20.0% | 80.0% |
| #49011 | floor · high | Oct 26, 2026 | 0.060Ξ | 0.065Ξ | +8.3% | 91.7% |
Model otherdeed-1793625239-2026-08-03.2 · evaluated through 11/2/2026. Method details on the methodology page.