Accuracy and Fairness in a Conditional Generative Adversarial Model of Crime Prediction

Abstract

We propose a novel conditional GANs architecture for crime (robberies) prediction in Bogotá, capital city of Colombia. The model uses several layers of ConvLSTM neural nets in both the generative and the discriminatory networks. We further condition on past crime intensity maps, weekdays, and holidays. The trained network is able to capture spatiotemporal patterns and outperforms state-of-the-art predictive models such as spatiotemporal Poisson point process, as well as other models trained with the same dataset. Model's accuracy reaches an area under the Hit Rate - Percentage Area Covered by Hotspots curve of 0.86. However, our predictions suggest that there is a potential bias with heterogeneous effects on vulnerable populations. We address the fairness consequence of this model in low income vs. high income residents by estimating a calibration test conditional to these protected variables. Finally, we introduce a fairness - accuracy balancing technique that quantifies the tradeoffs between accuracy and fairness in this type of models. This technique notably reduces bias with a marginal effect on accuracy.