Next Hit Predictor - Self-exciting Risk Modeling for Predicting Next Locations of Serial Crimes

TL;DR

This paper introduces Next Hit Predictor, a self-exciting risk model that predicts the next crime location in a series by combining spatial-temporal features and previous offense data, trained with a convex ranking objective.

Contribution

The paper presents a novel self-exciting point process model for serial crime location prediction, with a new training method using convex optimization and stochastic gradient descent.

Findings

Demonstrated promising results on real serial crime data

Effectively incorporates spatial-temporal features and historical offense data

Outperforms baseline models in predicting next crime locations

Abstract

Our goal is to predict the location of the next crime in a crime series, based on the identified previous offenses in the series. We build a predictive model called Next Hit Predictor (NHP) that finds the most likely location of the next serial crime via a carefully designed risk model. The risk model follows the paradigm of a self-exciting point process which consists of a background crime risk and triggered risks stimulated by previous offenses in the series. Thus, NHP creates a risk map for a crime series at hand. To train the risk model, we formulate a convex learning objective that considers pairwise rankings of locations and use stochastic gradient descent to learn the optimal parameters. Next Hit Predictor incorporates both spatial-temporal features and geographical characteristics of prior crime locations in the series. Next Hit Predictor has demonstrated promising results on decades' worth of serial crime data collected by the Crime Analysis Unit of the Cambridge Police Department in Massachusetts, USA.