204 – Experimental Design
Satellite Images and Deep Learning to Identify Discrepancy in Mailing Addresses with Applications to Census 2020 in Houston
Zhaozhuo Xu
Rice University
The accuracy and completeness of population estimation would significantly impact the allocation of public resources. However, the current census paradigm experiences a non-negligible level of under-counting. Existing solutions to this problem by the Census Bureau is to increase canvassing efforts, which leads to expensive and inefficient usage of human resources. In this work, we argue that the existence of hidden multi-family households is a major cause of under-counting. Accordingly, we introduce a low-cost but high accuracy method that combines satellite imagery and deep learning technologies to identify all hidden multi-family (HMF) households. With comprehensive knowledge on the HMF households, the efficiency and effectiveness of the decennial census could be vastly improved. An extensive experiment demonstrates that our approach can discover over 1800 undetected HMF in a single zip code of the Houston area.