Improving Crime Count Forecasts Using Twitter and Taxi Data

TL;DR

This study demonstrates that integrating human activity data from Twitter, taxi trips, and Foursquare enhances property crime prediction accuracy in NYC by 19%, but does not improve violent crime forecasts.

Contribution

It introduces a novel approach combining social media and mobility data to improve property crime forecasting models.

Findings

Improved property crime prediction accuracy by 19%.

Combined data sources yield the strongest predictive insights.

No improvement observed for violent crime predictions.

Abstract

Crime prediction is crucial to criminal justice decision makers and efforts to prevent crime. The paper evaluates the explanatory and predictive value of human activity patterns derived from taxi trip, Twitter and Foursquare data. Analysis of a six-month period of crime data for New York City shows that these data sources improve predictive accuracy for property crime by 19% compared to using only demographic data. This effect is strongest when the novel features are used together, yielding new insights into crime prediction. Notably and in line with social disorganization theory, the novel features cannot improve predictions for violent crimes.