Graduation Year
2022
Date of Submission
12-2021
Document Type
Open Access Senior Thesis
Degree Name
Bachelor of Arts
Department
Economics
Reader 1
Michael Gelman
Abstract
We propose a methodology for estimating neighborhood gentrification using high frequency, publicly available Airbnb data. Leveraging 3.8 million text reviews from Jan 2014 to Dec 2019 across 17 US cities, we find guest reviews and rental characteristics to be predictive of gentrification during the same period. Both structured features (e.g. number of listings) and unstructured features (e.g. word frequency in reviews) are found to be important predictors across multiple specifications. Using our trained model, we predict and map current gentrification rates ahead of official statistics. These models are provided freely to enable rapid policy response and further research.
Recommended Citation
Kitchell, Leo, "High Frequency Gentrification Prediction Using Airbnb Data" (2022). CMC Senior Theses. 2812.
https://scholarship.claremont.edu/cmc_theses/2812
Data Repository Link
https://github.com/LeoKitchell/SeniorThesis/
