Goto

Collaborating Authors

 Columbus County


Predicting the Past: Estimating Historical Appraisals with OCR and Machine Learning

Bhaskar, Mihir, Luo, Jun Tao, Geng, Zihan, Hajra, Asmita, Howell, Junia, Gormley, Matthew R.

arXiv.org Artificial Intelligence

Despite well-documented consequences of the U.S. government's 1930s housing policies on racial wealth disparities, scholars have struggled to quantify its precise financial effects due to the inaccessibility of historical property appraisal records. Many counties still store these records in physical formats, making large-scale quantitative analysis difficult. We present an approach scholars can use to digitize historical housing assessment data, applying it to build and release a dataset for one county. Starting from publicly available scanned documents, we manually annotated property cards for over 12,000 properties to train and validate our methods. We use OCR to label data for an additional 50,000 properties, based on our two-stage approach combining classical computer vision techniques with deep learning-based OCR. For cases where OCR cannot be applied, such as when scanned documents are not available, we show how a regression model based on building feature data can estimate the historical values, and test the generalizability of this model to other counties. With these cost-effective tools, scholars, community activists, and policy makers can better analyze and understand the historical impacts of redlining.


Lame duck, indeed

FOX News

Co-chairs of The Problem Solvers Caucus Republican Rep. Tom Reed and Democrat Rep. Josh Gottheimer speak out on moving past gridlock in Washington. On the roster: Lame duck, indeed - H.W. Bush-era AG eyed as possible Sessions successor - GOP officials had early warning of voter fraud in N.C. - SupCo's double-jeopardy case holds Mueller probe implications - Will study for bacon LAME DUCK, INDEED In the universe of Washington dud stories, "government shutdown looming" is right up there with "fireworks expected at hearing" and "leadership challenge brewing." The witness shrugs off lame speechifying disguised as tough questioning, the insurgency peters out over the question "who else" and in all but five cases since 1990 the government makes it past the fiscal cliff by plopping out some temporary spending measure. And yet… Congress today passed a two-week extension of current spending while the lame-duck House and Senate bicker over how to proceed. At issue are seven stalled annual appropriations bills that fund nine cabinet agencies.