Summary of Geospatial Disparities: a Case Study on Real Estate Prices in Paris, by Agathe Fernandes Machado et al.
Geospatial Disparities: A Case Study on Real Estate Prices in Paris
by Agathe Fernandes Machado, François Hu, Philipp Ratz, Ewen Gallic, Arthur Charpentier
First submitted to arxiv on: 29 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computers and Society (cs.CY)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper highlights the growing importance of geospatial data in predictive models, driven by increased IoT sensors and decreasing computing costs. While this data improves model performance, it also risks perpetuating historical biases and exclusionary practices, exacerbating socio-economic disparities. The authors emphasize the need to identify and rectify these biases in complex algorithms. They propose a toolkit for mitigating geospatial bias, extending classical fairness definitions with ordinal regression cases using spatial attributes. This approach allows for measuring disparities from data aggregation levels and advocating for less intrusive correction methods. The methodology is illustrated using a Parisian real estate dataset, showcasing practical applications and scrutinizing the implications of choosing geographical aggregation levels for fairness and calibration measures. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how geospatial data, like location-based information from sensors and trackers, can help improve predictive models. However, this increased accuracy also risks reproducing old biases and inequalities. The authors want to make sure that these predictions don’t unfairly favor certain groups or areas. They’re proposing a new way to analyze and correct for these biases using geospatial data. This approach is important because it can help mitigate the negative impacts of predictive models on society. |
Keywords
* Artificial intelligence * Regression
