Nowcasting Gentrification: Using Yelp Data to Quantify Neighborhood Change

Edward L. Glaeser; Hyunjin  Kim; Michael  Luca

Article | American Economic Association Papers and Proceedings | May 2018

Nowcasting Gentrification: Using Yelp Data to Quantify Neighborhood Change

by Edward L. Glaeser, Hyunjin Kim and Michael Luca

Abstract

Data from digital platforms have the potential to improve our understanding of gentrification and enable new measures of how neighborhoods change in close to real time. Combining data on businesses from Yelp with data on gentrification from the Census, Federal Housing Finance Agency, and Streetscore (an algorithm using Google Streetview), we find that gentrifying neighborhoods tend to have growing numbers of local groceries, cafés, restaurants, and bars, with little evidence of crowd-out of other types of businesses. For example, the entry of a new coffee shop into a zip code in a given year is associated with a 0.5% increase in housing prices. Moreover, Yelp measures of local business activity provide leading indicators for housing price changes and help to forecast which neighborhoods are gentrifying.

Keywords: Forecasting Models; Simulation Methods; Regional Economic Activity: Growth, Development, Environmental Issues, and Changes; Geographic Location; Local Range; Transition; Data and Data Sets; Measurement and Metrics; Economic Growth; Forecasting and Prediction;

Format: Print

Purchase

Citation:

Glaeser, Edward L., Hyunjin Kim, and Michael Luca. "Nowcasting Gentrification: Using Yelp Data to Quantify Neighborhood Change." American Economic Association Papers and Proceedings 108 (May 2018): 77–82.

Because consumer reviews leverage the wisdom of the crowd, the way in which they are aggregated is a central decision faced by platforms. We explore this "rating aggregation problem" and offer a structural approach to solving it, allowing for (1) reviewers to vary in stringency and accuracy, (2) reviewers to be influenced by existing reviews, and (3) product quality to change over time. Applying this to restaurant reviews from Yelp.com, we construct an adjusted average rating and show that even a simple algorithm can lead to large information efficiency gains relative to the arithmetic average.

Disclosure policies have the potential to help consumers and make markets more efficient. Yet, the effectiveness of disclosure policies can be undermined if firms strategically make unfavorable information unnecessarily complicated to understand. To explore the incentives for using complexity in disclosure, we implement a game of mandatory disclosure where senders are required to report their private information truthfully but can choose how complex to make their reports. We find that senders use complex disclosure over half the time, and most of this obfuscation is profitable because receivers make systematic mistakes in assessing complex reports. Stated beliefs suggest that receivers correctly infer the strategic implications of complexity but are overconfident about their ability to assess complex reports.

Faculty & Research

Nowcasting Gentrification: Using Yelp Data to Quantify Neighborhood Change

Abstract

Citation:

About the Authors

More from these Authors