Once Upon a Crime: Towards Crime Prediction from Demographics and Mobile Data

Abstract

In this paper, we present a novel approach to predict crime in a geographic space from multiple data sources, in particular mobile phone and demographic data. The main contribution of the proposed approach lies in using aggregated and anonymized human behavioral data derived from mobile network activity to tackle the crime prediction problem. While previous research efforts have used either background historical knowledge or offenders' profiling, our findings support the hypothesis that aggregated human behavioral data captured from the mobile network infrastructure, in combination with basic demographic information, can be used to predict crime. In our experimental results with real crime data from London we obtain an accuracy of almost 70% when predicting whether a specific area in the city will be a crime hotspot or not. Moreover, we provide a discussion of the implications of our findings for data-driven crime analysis.

arXiv comment10 pages, 3 figures. To appear in ACM International Conference on Multimodal Interaction (ICMI 2014)

References in corpus (3)

• Twitter mood predicts the stock market
• The predictability of consumer visitation patterns
• Patterns of Individual Shopping Behavior

Cited by in corpus (8)

• Statistical physics of crime: A review
• Crime Prediction Based On Crime Types And Using Spatial And Temporal Criminal Hotspots
• Improving Crime Count Forecasts Using Twitter and Taxi Data
• Forecasting Crime with Deep Learning
• Simulating Crowds in Real Time with Agent-Based Modelling and a Particle Filter
• Towards Real-time Customer Experience Prediction for Telecommunication Operators
• Mobile Money: Understanding and Predicting its Adoption and Use in a Developing Economy
• Public decision support for low population density areas: An imbalance-aware hyper-ensemble for spatio-temporal crime prediction