AppraisrAppraisr
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)
93.8%
Mean accuracy (100−APE)
86.7%
Within ±5%
44%
Within ±10%
60%
Within ±20%
81%
Bias
+0.5%

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
floor166894.7%65%+0.1%
middle5860.5%9%-4.0%
grail27788.3%44%+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

ItemTier / evidenceDateSaleModelErrorAccuracy
#27274floor · highSep 17, 20260.068Ξ0.080Ξ+18.3%81.7%
#48089floor · highSep 17, 20260.068Ξ0.082Ξ+21.3%78.7%
#11356floor · highSep 17, 20260.066Ξ0.080Ξ+20.9%79.2%
#28670grail · highSep 17, 20260.068Ξ0.082Ξ+21.3%78.7%
#30593floor · highSep 17, 20260.068Ξ0.079Ξ+16.9%83.1%
#55257floor · highSep 17, 20260.066Ξ0.079Ξ+19.7%80.3%
#54345floor · highSep 17, 20260.066Ξ0.078Ξ+18.0%82.0%
#47393floor · highSep 16, 20260.078Ξ0.083Ξ+6.1%93.9%
#46075middle · highSep 16, 20260.073Ξ0.182Ξ+149.7%0.0%
#46117floor · highSep 16, 20260.100Ξ0.081Ξ-19.0%81.0%
#57734floor · highSep 16, 20260.148Ξ0.075Ξ-49.3%50.7%
#83262floor · highSep 15, 20260.095Ξ0.077Ξ-18.6%81.4%
#10339floor · highSep 15, 20260.080Ξ0.079Ξ-0.9%99.1%
#88345floor · highSep 15, 20260.080Ξ0.080Ξ+0.5%99.5%
#47375floor · highSep 15, 20260.073Ξ0.077Ξ+5.9%94.1%
#55508grail · highSep 14, 20260.440Ξ0.108Ξ-75.5%24.6%
#57734floor · highSep 14, 20260.071Ξ0.107Ξ+50.9%49.1%
#94135grail · highSep 14, 20260.073Ξ0.080Ξ+9.3%90.7%
#2381floor · highSep 14, 20260.189Ξ0.094Ξ-50.3%49.7%
#50153floor · highSep 13, 20260.074Ξ0.077Ξ+3.4%96.6%
#9928floor · highSep 13, 20260.121Ξ0.084Ξ-30.6%69.4%
#55196floor · highSep 12, 20260.094Ξ0.075Ξ-20.4%79.6%
#68576floor · highSep 12, 20260.083Ξ0.075Ξ-9.6%90.4%
#6984middle · highSep 12, 20260.243Ξ0.150Ξ-38.4%61.6%
#88855floor · highSep 11, 20260.090Ξ0.086Ξ-4.3%95.7%
#2265floor · highSep 11, 20260.165Ξ0.109Ξ-33.9%66.1%
#85844floor · highSep 11, 20260.080Ξ0.072Ξ-9.7%90.3%
#76212floor · highSep 10, 20260.085Ξ0.077Ξ-9.0%91.0%
#45809floor · highSep 10, 20260.083Ξ0.074Ξ-10.4%89.6%
#47393floor · highSep 10, 20260.083Ξ0.075Ξ-9.3%90.7%
#88855floor · highSep 10, 20260.086Ξ0.071Ξ-17.9%82.1%
#89125middle · highSep 10, 20260.533Ξ0.103Ξ-80.7%19.3%
#3173middle · highSep 10, 20260.185Ξ0.129Ξ-30.4%69.7%
#66262floor · highSep 10, 20260.100Ξ0.068Ξ-32.0%68.0%
#63714floor · highSep 10, 20260.103Ξ0.077Ξ-25.2%74.8%
#16250floor · highSep 10, 20260.093Ξ0.084Ξ-9.7%90.3%
#19497floor · highSep 10, 20260.094Ξ0.083Ξ-11.6%88.4%
#19497floor · highSep 10, 20260.082Ξ0.084Ξ+2.3%97.7%
#54795grail · insufficientSep 10, 20261.350Ξ0.648Ξ-52.0%48.0%
#63017grail · lowSep 10, 20260.990Ξ0.375Ξ-62.1%37.9%

Model otherdeed-1789609439-2026-08-03.2 · evaluated through 9/17/2026. Method details on the methodology page.