Computer Vision Uncovers Predictors of Physical Urban Change

Nikhil  Naik; Scott Duke Kominers; Ramesh  Raskar; Edward L. Glaeser; César A. Hidalgo

Article | Proceedings of the National Academy of Sciences of the United States of America | 2017

Computer Vision Uncovers Predictors of Physical Urban Change

by Nikhil Naik, Scott Duke Kominers, Ramesh Raskar, Edward L. Glaeser and César A. Hidalgo

Abstract

Which neighborhoods experience physical improvements? In this paper, we introduce a computer vision method to measure changes in the physical appearances of neighborhoods from time-series street-level imagery. We connect changes in the physical appearance of five U.S. cities with economic and demographic data and find three factors that predict neighborhood improvement. First, neighborhoods that are densely populated by college-educated adults are more likely to experience physical improvements—an observation that is compatible with the economic literature linking human capital and local success. Second, neighborhoods with better initial appearances experience, on average, larger positive improvements—an observation that is consistent with “tipping” theories of urban change. Third, neighborhood improvement correlates positively with physical proximity to the central business district and to other physically attractive neighborhoods—an observation that is consistent with the “invasion” theories of urban sociology. Together, our results provide support for three classical theories of urban change and illustrate the value of using computer vision methods and street-level imagery to understand the physical dynamics of cities.

Keywords: urban economics; gentrification; urban studies; computer vision; nieghborhood effects; Urban Development; Situation or Environment; Demographics; Economics; Change;

Format: Print

Find at Harvard Read Now

Citation:

Naik, Nikhil, Scott Duke Kominers, Ramesh Raskar, Edward L. Glaeser, and César A. Hidalgo. "Computer Vision Uncovers Predictors of Physical Urban Change." Proceedings of the National Academy of Sciences of the United States of America 114, no. 29 (July 18, 2017).

The U.S. residential real estate agency market presents a puzzle for economic theory: commissions on real estate transactions have remained constant and high for decades even though agent entry is frequent and agents’ costs of providing service are low. We model the real estate agency market, and other brokered markets, via repeated extensive form games; in our game, brokers first post prices for customers and then choose which agents on the other side of the market to work with. We show that prices appreciably higher than the competitive prices can be sustained (for a fixed discount factor) regardless of the number of brokers; this is done through strategies that condition willingness to transact with each broker on that broker’s initial posted prices. Our results can thus rationalize why brokered markets exhibit pricing high above marginal cost despite fierce competition for customers; moreover, our model can help explain why agents and platforms who have tried to reduce commissions have had trouble entering the market.

We introduce a new model of school choice with reserves in which a social planner is constrained by a limited supply of reserve seats and tries to find an optimal matching according to a social welfare function. We construct the optimal distribution of reserves via a quartic-time dynamic programming algorithm. Due to the modular nature of the dynamic program, the mechanism is strategy-proof for reserve-eligible students.

This case is set in mid-2019, when Qualcomm was struggling with unwanted takeover battles, fights with Apple and the Chinese government, and internal dissension on the board of directors. Ten years earlier Qualcomm was hailed as a monopoly on CDMA technologies and its derivatives—it appeared to be positioned to become the next dominant technology company in the tradition of Microsoft and Intel. But as the industry changed, Qualcomm’s competitive position seriously weakened. The purpose of the case is to explore central questions in strategy formulation: 1. how to build a long-term sustainable position based on technology, 2. how to design an IP strategy to lock in customers for the long run, 3. how to build a global standard and appropriate returns on that standard, and 4. how to respond when your historical business model starts to crumble.

Faculty & Research

Computer Vision Uncovers Predictors of Physical Urban Change

Abstract

Citation:

About the Author

More from the Author