Estimating the Impact of a Flood Event on Property Value and Its Diminished Effect over Time (Short Paper)

Authors Nazia Ferdause Sodial, Oleksandr Galkin, Aidan Slingsby



PDF
Thumbnail PDF

File

LIPIcs.GIScience.2023.68.pdf
  • Filesize: 2.73 MB
  • 6 pages

Document Identifiers

Author Details

Nazia Ferdause Sodial
  • City, University of London, UK
Oleksandr Galkin
  • City, University of London, UK
Aidan Slingsby
  • City, University of London, UK

Acknowledgements

This research was conducted under the initiative of MIAC Analytics LTD. The flood data was acquired by MIAC Analytics LTD from its data partners, WhenFresh.

Cite AsGet BibTex

Nazia Ferdause Sodial, Oleksandr Galkin, and Aidan Slingsby. Estimating the Impact of a Flood Event on Property Value and Its Diminished Effect over Time (Short Paper). In 12th International Conference on Geographic Information Science (GIScience 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 277, pp. 68:1-68:6, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)
https://doi.org/10.4230/LIPIcs.GIScience.2023.68

Abstract

With the increase in natural disasters, flood events have become more frequent and severe calling for mortgage industries to take immediate steps to mitigate the financial risk posed by floods. This study looked more closely at the underlying effects of flood disasters on historical house prices as part of a climatic stress test. The discount applied on house prices due to a flood event was achieved by leveraging a causal inference approach supported by machine learning algorithms on repeat sales property and historic flood data. While the Average Treatment Effect (ATE) was employed to estimate the effect of a flood event on house prices in an area, the Conditional Average Treatment Effect (CATE) aided in overcoming the heterogeneous nature of the data by calculating the flood effect on property prices of each postcode. LightGBM as a base estimator of the causal model worked as an advantage to capture the nonlinear relationship between the features and the outcome variable and further allowed us to interpret the contribution of each feature towards the decay of these discounts using SHAP values.

Subject Classification

ACM Subject Classification
  • Computing methodologies → Machine learning approaches
Keywords
  • Flood
  • Causal Inference
  • Machine Learning
  • Property Analytics

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads

References

  1. Allan Beltrán, David Maddison, and Robert Elliott. The impact of flooding on property prices: A repeat-sales approach. Journal of Environmental Economics and Management, 95:62-86, 2019. Google Scholar
  2. Nam Bui, Le Wen, and Basil Sharp. House prices and flood risk exposure: An integration of hedonic property model and spatial econometric analysis. The Journal of Real Estate Finance and Economics, pages 1-32, 2022. Google Scholar
  3. Karl E Case and Robert J Shiller. Prices of single family homes since 1970: New indexes for four cities, 1987. Google Scholar
  4. CCRA3. Housing briefing. https://www.ukclimaterisk.org/wp-content/uploads/2021/06/CCRA3-Briefing-Housing.pdf, 2021. [Online; accessed 17-April-2023].
  5. Jessica Lamond, David Proverbs, and Adarkwah Antwi. Measuring the impact of flooding on uk house prices: A new framework for small sample problems. Property Management, 2007. Google Scholar
  6. Uber. Meta-learner algorithms. https://causalml.readthedocs.io/en/latest/methodology.html, 2022. [Online; accessed 06-Nov-2022].