AppraisrAppraisr
Accuracy

How accurate is the BEANZ Official 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)
92.9%
Mean accuracy (100−APE)
88.4%
Within ±5%
37%
Within ±10%
61%
Within ±20%
83%
Bias
-5.3%

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
floor205693.3%64%-5.1%
middle6278.3%23%+1.5%
grail7680.0%22%-17.7%

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
#3349floor · highSep 21, 20260.040Ξ0.046Ξ+15.9%84.1%
#7109floor · highSep 21, 20260.040Ξ0.040Ξ+1.2%98.8%
#6222floor · highSep 21, 20260.040Ξ0.042Ξ+6.3%93.7%
#598grail · highSep 21, 20260.160Ξ0.334Ξ+108.9%0.0%
#1910floor · highSep 21, 20260.042Ξ0.042Ξ+1.2%98.8%
#17052floor · highSep 21, 20260.040Ξ0.045Ξ+11.9%88.1%
#1531floor · highSep 21, 20260.042Ξ0.040Ξ-3.7%96.3%
#9509floor · highSep 21, 20260.043Ξ0.040Ξ-6.9%93.1%
#1170floor · highSep 20, 20260.044Ξ0.041Ξ-6.2%93.8%
#16906floor · highSep 19, 20260.041Ξ0.042Ξ+2.9%97.1%
#7872floor · highSep 19, 20260.044Ξ0.041Ξ-6.2%93.8%
#7872floor · highSep 19, 20260.041Ξ0.040Ξ-2.0%98.0%
#10649floor · highSep 19, 20260.050Ξ0.041Ξ-17.2%82.8%
#12754floor · highSep 18, 20260.050Ξ0.042Ξ-16.0%84.0%
#1170floor · highSep 18, 20260.040Ξ0.043Ξ+8.0%92.0%
#13041floor · highSep 18, 20260.043Ξ0.043Ξ0.0%100.0%
#11070floor · highSep 18, 20260.042Ξ0.041Ξ-2.4%97.6%
#18031floor · highSep 18, 20260.041Ξ0.040Ξ-2.8%97.2%
#1171floor · highSep 18, 20260.040Ξ0.040Ξ+0.8%99.2%
#5466floor · highSep 18, 20260.041Ξ0.040Ξ-2.4%97.6%
#17584floor · highSep 18, 20260.051Ξ0.045Ξ-12.1%87.9%
#7101floor · highSep 18, 20260.043Ξ0.042Ξ-1.4%98.6%
#750floor · highSep 18, 20260.117Ξ0.053Ξ-54.9%45.1%
#13564floor · highSep 18, 20260.040Ξ0.041Ξ+3.5%96.5%
#515floor · highSep 18, 20260.100Ξ0.043Ξ-57.0%43.0%
#10465floor · highSep 17, 20260.064Ξ0.045Ξ-29.7%70.3%
#11961floor · highSep 17, 20260.039Ξ0.040Ξ+2.3%97.7%
#9673middle · highSep 17, 20260.055Ξ0.116Ξ+110.9%0.0%
#9682floor · highSep 17, 20260.040Ξ0.042Ξ+5.0%95.0%
#3808floor · highSep 17, 20260.041Ξ0.040Ξ-2.4%97.6%
#9463floor · highSep 17, 20260.039Ξ0.044Ξ+13.4%86.6%
#13137floor · highSep 16, 20260.058Ξ0.046Ξ-20.7%79.3%
#16411floor · highSep 16, 20260.070Ξ0.049Ξ-30.0%70.0%
#8763floor · highSep 16, 20260.039Ξ0.049Ξ+26.3%73.7%
#10649floor · highSep 16, 20260.040Ξ0.046Ξ+15.9%84.1%
#16942floor · highSep 16, 20260.064Ξ0.054Ξ-15.5%84.5%
#10743floor · highSep 16, 20260.042Ξ0.041Ξ-2.4%97.6%
#18752floor · highSep 15, 20260.041Ξ0.044Ξ+8.6%91.4%
#18031floor · highSep 15, 20260.041Ξ0.042Ξ+3.5%96.6%
#17833middle · highSep 15, 20260.062Ξ0.082Ξ+32.3%67.7%

Model beanz-1789968779-2026-08-03.2 · evaluated through 9/21/2026. Method details on the methodology page.