A hand-annotated dataset of 1933 Hamilton County property appraisals is extracted with template-aligned OCR, and a random forest trained on contemporary features estimates those historical values with about 17% MAPE.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Predicting the Past: Estimating Historical Appraisals with OCR and Machine Learning
A hand-annotated dataset of 1933 Hamilton County property appraisals is extracted with template-aligned OCR, and a random forest trained on contemporary features estimates those historical values with about 17% MAPE.