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)
93.6%
Mean accuracy (100−APE)
90.8%
Within ±5%
39%
Within ±10%
68%
Within ±20%
91%
Bias
-1.7%

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
floor143993.7%69%-1.4%
middle2776.0%22%-2.3%
grail2185.1%33%-19.0%

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, 20260.230Ξ0.199Ξ-13.5%86.5%
#9956floor · highAug 2, 20260.193Ξ0.216Ξ+11.9%88.1%
#6775floor · highAug 1, 20260.194Ξ0.200Ξ+3.1%96.9%
#6865floor · highAug 1, 20260.232Ξ0.226Ξ-2.6%97.4%
#4346floor · highAug 1, 20260.220Ξ0.198Ξ-10.0%90.0%
#1243floor · highAug 1, 20260.183Ξ0.200Ξ+9.3%90.7%
#2294floor · highAug 1, 20260.188Ξ0.194Ξ+3.2%96.8%
#253floor · highAug 1, 20260.188Ξ0.195Ξ+3.7%96.3%
#8239floor · highAug 1, 20260.189Ξ0.194Ξ+2.7%97.4%
#6775floor · highAug 1, 20260.200Ξ0.189Ξ-5.5%94.5%
#4346floor · highAug 1, 20260.185Ξ0.218Ξ+17.8%82.2%
#2907floor · highAug 1, 20260.250Ξ0.200Ξ-20.0%80.0%
#2079floor · highJul 31, 20260.196Ξ0.190Ξ-2.9%97.1%
#6912floor · highJul 31, 20260.199Ξ0.187Ξ-5.9%94.1%
#1217floor · highJul 31, 20260.199Ξ0.192Ξ-3.4%96.6%
#1217floor · highJul 31, 20260.188Ξ0.197Ξ+4.8%95.2%
#6775floor · highJul 31, 20260.188Ξ0.194Ξ+3.2%96.8%
#2079floor · highJul 31, 20260.188Ξ0.204Ξ+8.5%91.5%
#5789floor · highJul 31, 20260.187Ξ0.262Ξ+40.1%59.9%
#255floor · highJul 31, 20260.200Ξ0.200Ξ0.0%100.0%
#2079floor · highJul 31, 20260.200Ξ0.188Ξ-5.9%94.1%
#1243floor · highJul 31, 20260.200Ξ0.192Ξ-3.8%96.2%
#6775floor · highJul 31, 20260.199Ξ0.193Ξ-3.3%96.7%
#2294floor · highJul 31, 20260.199Ξ0.192Ξ-3.8%96.2%
#253floor · highJul 30, 20260.194Ξ0.187Ξ-3.6%96.4%
#8239floor · highJul 30, 20260.194Ξ0.198Ξ+2.1%97.9%
#2294floor · highJul 30, 20260.186Ξ0.216Ξ+16.1%83.9%
#3154floor · highJul 30, 20260.200Ξ0.195Ξ-2.5%97.5%
#3154floor · highJul 30, 20260.187Ξ0.199Ξ+6.4%93.6%
#808floor · highJul 30, 20260.200Ξ0.192Ξ-3.9%96.1%
#694floor · highJul 30, 20260.195Ξ0.189Ξ-3.0%97.0%
#7137floor · highJul 30, 20260.186Ξ0.195Ξ+4.8%95.2%
#7283floor · highJul 30, 20260.186Ξ0.230Ξ+23.7%76.3%
#253floor · highJul 30, 20260.187Ξ0.256Ξ+36.9%63.1%
#808floor · highJul 30, 20260.188Ξ0.219Ξ+16.5%83.5%
#694floor · highJul 30, 20260.192Ξ0.225Ξ+17.2%82.8%
#1586floor · highJul 29, 20260.208Ξ0.205Ξ-1.3%98.7%
#1260floor · highJul 28, 20260.211Ξ0.203Ξ-3.8%96.2%
#8720floor · highJul 28, 20260.211Ξ0.200Ξ-5.3%94.8%
#70floor · highJul 28, 20260.211Ξ0.209Ξ-1.0%99.0%

Model mfers-1785642719-2026-08-03.2 · evaluated through 8/2/2026. Method details on the methodology page.