AppraisrAppraisr
Accuracy

How accurate is the rektguy 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%
38%
Within ±10%
67%
Within ±20%
90%
Bias
+0.7%

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
floor152893.3%69%+0.7%
middle3364.3%24%-7.6%
grail642.2%0%+44.4%

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
#2269floor · highAug 2, 20260.210Ξ0.213Ξ+1.4%98.6%
#738floor · highAug 2, 20260.202Ξ0.205Ξ+1.5%98.5%
#660floor · highAug 2, 20260.192Ξ0.199Ξ+3.7%96.4%
#4885floor · mediumAug 1, 20260.196Ξ0.203Ξ+3.6%96.4%
#7654floor · highAug 1, 20260.191Ξ0.215Ξ+12.6%87.4%
#738floor · highJul 31, 20260.200Ξ0.197Ξ-1.5%98.5%
#2832floor · highJul 31, 20260.205Ξ0.198Ξ-3.4%96.6%
#5576floor · highJul 31, 20260.208Ξ0.235Ξ+13.0%87.0%
#6133floor · highJul 31, 20260.206Ξ0.201Ξ-2.4%97.6%
#1349floor · highJul 31, 20260.203Ξ0.195Ξ-3.9%96.1%
#6530floor · highJul 31, 20260.213Ξ0.206Ξ-3.3%96.7%
#5576floor · highJul 31, 20260.235Ξ0.207Ξ-11.8%88.2%
#976floor · highJul 31, 20260.215Ξ0.198Ξ-7.9%92.1%
#7654floor · highJul 30, 20260.215Ξ0.204Ξ-5.2%94.8%
#2016floor · highJul 30, 20260.197Ξ0.214Ξ+8.6%91.4%
#7654floor · highJul 30, 20260.202Ξ0.202Ξ0.0%100.0%
#8020floor · highJul 30, 20260.195Ξ0.209Ξ+7.2%92.8%
#976floor · highJul 30, 20260.199Ξ0.191Ξ-4.0%96.0%
#2914floor · highJul 30, 20260.199Ξ0.246Ξ+23.7%76.4%
#7302floor · highJul 30, 20260.199Ξ0.220Ξ+10.6%89.4%
#904floor · highJul 30, 20260.199Ξ0.198Ξ-0.5%99.5%
#904floor · highJul 29, 20260.186Ξ0.204Ξ+9.7%90.3%
#7001middle · highJul 29, 20260.187Ξ0.315Ξ+68.5%31.6%
#904floor · highJul 29, 20260.200Ξ0.209Ξ+4.5%95.5%
#1055floor · highJul 29, 20260.189Ξ0.213Ξ+12.7%87.3%
#1717floor · highJul 29, 20260.199Ξ0.217Ξ+9.1%90.9%
#1363floor · mediumJul 28, 20260.360Ξ0.232Ξ-35.6%64.4%
#4717floor · highJul 28, 20260.198Ξ0.187Ξ-5.6%94.4%
#5198floor · highJul 28, 20260.190Ξ0.200Ξ+5.3%94.7%
#4717floor · highJul 28, 20260.185Ξ0.203Ξ+9.7%90.3%
#976floor · highJul 28, 20260.186Ξ0.195Ξ+4.8%95.2%
#6731floor · highJul 27, 20260.198Ξ0.195Ξ-1.6%98.4%
#8707floor · highJul 27, 20260.199Ξ0.200Ξ+0.5%99.5%
#1622floor · highJul 27, 20260.198Ξ0.189Ξ-4.7%95.3%
#6841floor · highJul 27, 20260.205Ξ0.203Ξ-1.0%99.0%
#738floor · highJul 27, 20260.191Ξ0.205Ξ+7.3%92.7%
#976floor · highJul 27, 20260.191Ξ0.202Ξ+5.8%94.2%
#6377floor · highJul 27, 20260.206Ξ0.258Ξ+25.2%74.8%
#7720floor · highJul 27, 20260.206Ξ0.201Ξ-2.3%97.7%
#8298floor · highJul 27, 20260.206Ξ0.218Ξ+6.0%94.0%

Model rektguy-1785700595-2026-08-03.2 · evaluated through 8/2/2026. Method details on the methodology page.