# Beyond Spatial Auto-Regressive Models: Predicting Housing Prices with Satellite Imagery

arXiv: https://arxiv.org/abs/1610.04805 · HTML: https://mlsanity.com/paper/1610.04805/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2016.

## Built on by (most cited first, 8 of 8)

- [Sat2Cap: Mapping Fine-Grained Textual Descriptions from Satellite Images](https://mlsanity.com/paper/2307.15904/) (2023)
- [What Image Features Boost Housing Market Predictions?](https://mlsanity.com/paper/2107.07148/) (2021)
- [Integrating Floor Plans into Hedonic Models for Rent Price Appraisal](https://mlsanity.com/paper/2102.08162/) (2021)
- [A Comparison of Multi-View Learning Strategies for Satellite Image-Based Real Estate Appraisal](https://mlsanity.com/paper/2105.04984/) (2021)
- [House Price Prediction using Satellite Imagery](https://mlsanity.com/paper/2105.06060/) (2021)
- [HouseTS: A Large-Scale, Multimodal Spatiotemporal U.S. Housing Dataset and Benchmark](https://mlsanity.com/paper/2506.00765/) (2025)
- [Visual Perception of Building and Household Vulnerability from Streets](https://mlsanity.com/paper/2205.14460/) (2022)
- [Thailand Asset Value Estimation Using Aerial or Satellite Imagery](https://mlsanity.com/paper/2307.08650/) (2023)

## Abstract (arXiv)

When modeling geo-spatial data, it is critical to capture spatial correlations for achieving high accuracy. Spatial Auto-Regression (SAR) is a common tool used to model such data, where the spatial contiguity matrix (W) encodes the spatial correlations. However, the efficacy of SAR is limited by two factors. First, it depends on the choice of contiguity matrix, which is typically not learnt from data, but instead, is assumed to be known apriori. Second, it assumes that the observations can be explained by linear models. In this paper, we propose a Convolutional Neural Network (CNN) framework to model geo-spatial data (specifi- cally housing prices), to learn the spatial correlations automatically. We show that neighborhood information embedded in satellite imagery can be leveraged to achieve the desired spatial smoothing. An additional upside of our framework is the relaxation of linear assumption on the data. Specific challenges we tackle while implementing our framework include, (i) how much of the neighborhood is relevant while estimating housing prices? (ii) what is the right approach to capture multiple resolutions of satellite imagery? and (iii) what other data-sources can help improve the estimation of spatial correlations? We demonstrate a marked improvement of 57% on top of the SAR baseline through the use of features from deep neural networks for the cities of London, Birmingham and Liverpool.