Accuracy
How accurate is the mfers 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)
93.1%
Mean accuracy (100−APE)
90.4%
Within ±5%
37%
Within ±10%
65%
Within ±20%
91%
Bias
-1.5%
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 | 1439 | 93.3% | 67% | -1.2% |
| middle | 27 | 78.5% | 22% | -2.8% |
| grail | 21 | 84.2% | 29% | -19.2% |
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 |
|---|---|---|---|---|---|---|
| #694 | floor · high | Aug 2, 2026 | 0.230Ξ | 0.200Ξ | -13.0% | 87.0% |
| #9956 | floor · high | Aug 2, 2026 | 0.193Ξ | 0.222Ξ | +15.0% | 85.0% |
| #6775 | floor · high | Aug 1, 2026 | 0.194Ξ | 0.200Ξ | +3.1% | 96.9% |
| #6865 | floor · high | Aug 1, 2026 | 0.232Ξ | 0.228Ξ | -1.7% | 98.3% |
| #4346 | floor · high | Aug 1, 2026 | 0.220Ξ | 0.199Ξ | -9.6% | 90.5% |
| #1243 | floor · high | Aug 1, 2026 | 0.183Ξ | 0.200Ξ | +9.3% | 90.7% |
| #2294 | floor · high | Aug 1, 2026 | 0.188Ξ | 0.196Ξ | +4.3% | 95.7% |
| #253 | floor · high | Aug 1, 2026 | 0.188Ξ | 0.196Ξ | +4.3% | 95.7% |
| #8239 | floor · high | Aug 1, 2026 | 0.189Ξ | 0.194Ξ | +2.7% | 97.4% |
| #6775 | floor · high | Aug 1, 2026 | 0.200Ξ | 0.190Ξ | -5.0% | 95.0% |
| #4346 | floor · high | Aug 1, 2026 | 0.185Ξ | 0.220Ξ | +18.9% | 81.1% |
| #2907 | floor · high | Aug 1, 2026 | 0.250Ξ | 0.203Ξ | -18.8% | 81.2% |
| #2079 | floor · high | Jul 31, 2026 | 0.196Ξ | 0.192Ξ | -1.9% | 98.1% |
| #6912 | floor · high | Jul 31, 2026 | 0.199Ξ | 0.190Ξ | -4.4% | 95.6% |
| #1217 | floor · high | Jul 31, 2026 | 0.199Ξ | 0.193Ξ | -2.9% | 97.1% |
| #1217 | floor · high | Jul 31, 2026 | 0.188Ξ | 0.199Ξ | +5.9% | 94.2% |
| #6775 | floor · high | Jul 31, 2026 | 0.188Ξ | 0.196Ξ | +4.3% | 95.7% |
| #2079 | floor · high | Jul 31, 2026 | 0.188Ξ | 0.204Ξ | +8.5% | 91.5% |
| #5789 | floor · high | Jul 31, 2026 | 0.187Ξ | 0.268Ξ | +43.3% | 56.7% |
| #255 | floor · high | Jul 31, 2026 | 0.200Ξ | 0.202Ξ | +1.0% | 99.0% |
| #2079 | floor · high | Jul 31, 2026 | 0.200Ξ | 0.192Ξ | -3.9% | 96.1% |
| #1243 | floor · high | Jul 31, 2026 | 0.200Ξ | 0.197Ξ | -1.3% | 98.8% |
| #6775 | floor · high | Jul 31, 2026 | 0.199Ξ | 0.195Ξ | -2.3% | 97.7% |
| #2294 | floor · high | Jul 31, 2026 | 0.199Ξ | 0.190Ξ | -4.8% | 95.2% |
| #253 | floor · high | Jul 30, 2026 | 0.194Ξ | 0.189Ξ | -2.6% | 97.4% |
| #8239 | floor · high | Jul 30, 2026 | 0.194Ξ | 0.204Ξ | +5.2% | 94.8% |
| #2294 | floor · high | Jul 30, 2026 | 0.186Ξ | 0.218Ξ | +17.2% | 82.8% |
| #3154 | floor · high | Jul 30, 2026 | 0.200Ξ | 0.193Ξ | -3.5% | 96.5% |
| #3154 | floor · high | Jul 30, 2026 | 0.187Ξ | 0.199Ξ | +6.4% | 93.6% |
| #808 | floor · high | Jul 30, 2026 | 0.200Ξ | 0.195Ξ | -2.4% | 97.6% |
| #694 | floor · high | Jul 30, 2026 | 0.195Ξ | 0.193Ξ | -1.0% | 99.0% |
| #7137 | floor · high | Jul 30, 2026 | 0.186Ξ | 0.200Ξ | +7.5% | 92.5% |
| #7283 | floor · high | Jul 30, 2026 | 0.186Ξ | 0.231Ξ | +24.2% | 75.8% |
| #253 | floor · high | Jul 30, 2026 | 0.187Ξ | 0.262Ξ | +40.1% | 59.9% |
| #808 | floor · high | Jul 30, 2026 | 0.188Ξ | 0.219Ξ | +16.5% | 83.5% |
| #694 | floor · high | Jul 30, 2026 | 0.192Ξ | 0.222Ξ | +15.6% | 84.4% |
| #1586 | floor · high | Jul 29, 2026 | 0.208Ξ | 0.207Ξ | -0.3% | 99.7% |
| #1260 | floor · high | Jul 28, 2026 | 0.211Ξ | 0.205Ξ | -2.9% | 97.1% |
| #8720 | floor · high | Jul 28, 2026 | 0.211Ξ | 0.202Ξ | -4.3% | 95.7% |
| #70 | floor · high | Jul 28, 2026 | 0.211Ξ | 0.213Ξ | +0.9% | 99.1% |
Model mfers-1785642719-2026-08-03.1 · evaluated through 8/2/2026. Method details on the methodology page.