AppraisrAppraisr
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

TierSalesMedian accuracyWithin ±10%Bias
floor143993.3%67%-1.2%
middle2778.5%22%-2.8%
grail2184.2%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

ItemTier / evidenceDateSaleModelErrorAccuracy
#694floor · highAug 2, 20260.230Ξ0.200Ξ-13.0%87.0%
#9956floor · highAug 2, 20260.193Ξ0.222Ξ+15.0%85.0%
#6775floor · highAug 1, 20260.194Ξ0.200Ξ+3.1%96.9%
#6865floor · highAug 1, 20260.232Ξ0.228Ξ-1.7%98.3%
#4346floor · highAug 1, 20260.220Ξ0.199Ξ-9.6%90.5%
#1243floor · highAug 1, 20260.183Ξ0.200Ξ+9.3%90.7%
#2294floor · highAug 1, 20260.188Ξ0.196Ξ+4.3%95.7%
#253floor · highAug 1, 20260.188Ξ0.196Ξ+4.3%95.7%
#8239floor · highAug 1, 20260.189Ξ0.194Ξ+2.7%97.4%
#6775floor · highAug 1, 20260.200Ξ0.190Ξ-5.0%95.0%
#4346floor · highAug 1, 20260.185Ξ0.220Ξ+18.9%81.1%
#2907floor · highAug 1, 20260.250Ξ0.203Ξ-18.8%81.2%
#2079floor · highJul 31, 20260.196Ξ0.192Ξ-1.9%98.1%
#6912floor · highJul 31, 20260.199Ξ0.190Ξ-4.4%95.6%
#1217floor · highJul 31, 20260.199Ξ0.193Ξ-2.9%97.1%
#1217floor · highJul 31, 20260.188Ξ0.199Ξ+5.9%94.2%
#6775floor · highJul 31, 20260.188Ξ0.196Ξ+4.3%95.7%
#2079floor · highJul 31, 20260.188Ξ0.204Ξ+8.5%91.5%
#5789floor · highJul 31, 20260.187Ξ0.268Ξ+43.3%56.7%
#255floor · highJul 31, 20260.200Ξ0.202Ξ+1.0%99.0%
#2079floor · highJul 31, 20260.200Ξ0.192Ξ-3.9%96.1%
#1243floor · highJul 31, 20260.200Ξ0.197Ξ-1.3%98.8%
#6775floor · highJul 31, 20260.199Ξ0.195Ξ-2.3%97.7%
#2294floor · highJul 31, 20260.199Ξ0.190Ξ-4.8%95.2%
#253floor · highJul 30, 20260.194Ξ0.189Ξ-2.6%97.4%
#8239floor · highJul 30, 20260.194Ξ0.204Ξ+5.2%94.8%
#2294floor · highJul 30, 20260.186Ξ0.218Ξ+17.2%82.8%
#3154floor · highJul 30, 20260.200Ξ0.193Ξ-3.5%96.5%
#3154floor · highJul 30, 20260.187Ξ0.199Ξ+6.4%93.6%
#808floor · highJul 30, 20260.200Ξ0.195Ξ-2.4%97.6%
#694floor · highJul 30, 20260.195Ξ0.193Ξ-1.0%99.0%
#7137floor · highJul 30, 20260.186Ξ0.200Ξ+7.5%92.5%
#7283floor · highJul 30, 20260.186Ξ0.231Ξ+24.2%75.8%
#253floor · highJul 30, 20260.187Ξ0.262Ξ+40.1%59.9%
#808floor · highJul 30, 20260.188Ξ0.219Ξ+16.5%83.5%
#694floor · highJul 30, 20260.192Ξ0.222Ξ+15.6%84.4%
#1586floor · highJul 29, 20260.208Ξ0.207Ξ-0.3%99.7%
#1260floor · highJul 28, 20260.211Ξ0.205Ξ-2.9%97.1%
#8720floor · highJul 28, 20260.211Ξ0.202Ξ-4.3%95.7%
#70floor · highJul 28, 20260.211Ξ0.213Ξ+0.9%99.1%

Model mfers-1785642719-2026-08-03.1 · evaluated through 8/2/2026. Method details on the methodology page.