Predicting neighborhoods’ socioeconomic attributes using restaurant data

Significance High-resolution socioeconomic data are crucial for place-based policy design and implementation, but it remains scarce for many developing cities and countries. We show that an easily accessible and timely updated neighborhood attribute, restaurant, when combined with machine-learning models, can be used to effectively predict a range of socioeconomic attributes. This approach allows us to collect training samples from representative neighborhoods and then use our trained model to infer unsampled neighborhoods in the city in a granular, timely, and low-cost manner. The good cross-city transferability performance of our model can also help bridge the “data gap” between cities, by training the model in cities with rich survey data and then applying it to cities where such data are unavailable. Accessing high-resolution, timely socioeconomic data such as data on population, employment, and enterprise activity at the neighborhood level is critical for social scientists and policy makers to design and implement location-based policies. However, in many developing countries or cities, reliable local-scale socioeconomic data remain scarce. Here, we show an easily accessible and timely updated location attribute—restaurant—can be used to accurately predict a range of socioeconomic attributes of urban neighborhoods. We merge restaurant data from an online platform with 3 microdatasets for 9 Chinese cities. Using features extracted from restaurants, we train machine-learning models to estimate daytime and nighttime population, number of firms, and consumption level at various spatial resolutions. The trained model can explain 90 to 95% of the variation of those attributes across neighborhoods in the test dataset. We analyze the tradeoff between accuracy, spatial resolution, and number of training samples, as well as the heterogeneity of the predicted results across different spatial locations, demographics, and firm industries. Finally, we demonstrate the cross-city generality of this method by training the model in one city and then applying it directly to other cities. The transferability of this restaurant model can help bridge data gaps between cities, allowing all cities to enjoy big data and algorithm dividends.