In recent years, simulation techniques have been applied to investigate the spatiotemporal dynamics of crime. Researchers have instantiated mobile offenders in agent-based simulations for theory testing, experimenting with crime prevention strategies, and exploring crime prediction techniques, despite facing challenges due to the complex dynamics of crime and the lack of detailed information about offender mobility. This paper presents a simulation model to explore offender mobility, focusing on the interplay between the agent's awareness space and activity nodes. The simulation generates patterns of individual mobility aiming to cumulatively match crime patterns. To instantiate a realistic urban environment, we use open data to simulate the urban structure, location-based social networks data to represent activity nodes as a proxy for human activity, and taxi trip data as a proxy for human movement between regions of the city. We analyze and systematically compare 35 different mobility strategies and demonstrate the benefits of using large-scale human activity data to simulate offender mobility. The strategies combining taxi trip data or historic crime data with popular activity nodes perform best compared to other strategies, especially for robbery. Our approach provides a basis for building agent-based crime simulations that infer offender mobility in urban areas from real-world data.

Law enforcement in America is facing a day of reckoning over its systemic, institutionalized racism and ongoing brutality against the people it was designed to protect. Virtually every aspect of the system is now under scrutiny, from budgeting and staffing levels to the data-driven prevention tools it deploys. A handful of local governments have already placed moratoriums on facial recognition systems in recent months and on Wednesday, Santa Cruz, California became the first city in the nation to outright ban the use of predictive policing algorithms. While it's easy to see the privacy risks that facial recognition poses, predictive policing programs have the potential to quietly erode our constitutional rights and exacerbate existing racial and economic biases in the law enforcement community. Simply put, predictive policing technology uses algorithms to pore over massive amounts of data to predict when and where future crimes will occur.

But can computer algorithms really help reduce crime? Imagine a gang of bank robbers arriving at their next heist, only to find an armed response unit already waiting on the corner. Or picture walking down a dark alley and feeling afraid, then seeing the reassuring blue lights of a police car sent to watch over you. Now imagine if all of this became possible thanks to mathematics. Ever since the Philip K Dick novel The Minority Report, which was later turned into a Tom Cruise blockbuster, was published in the 1950s, futurists and philosophers have grappled with the concept of "pre crime".

Researchers are using predictive artificial intelligence to help police officers classify crimes and determine whether they are gang-related. Jeffrey Brantingham, a University of California at Los Angeles anthropology professor and pioneer in the field of predictive policing, presented research earlier this year that uses a neural network to predict if crimes are gang-related. The ultimate goal, Brantingham's team writes in their paper, is "to automatically classify gang-related crimes where some crucial pieces of crime information are not currently available or are missing." Titled "Partially Generative Neural Networks for Gang Crime Classification," the paper is the first from a research team Brantingham leads at the University of Southern California's Center for Artificial Intelligence and Society (CAIS). Bratingham's team is studying "Spatio-Temporal Game Theory & Real-Time Machine Learning for Adversarial Groups," with a focus on countering extremism.

Jeff Brantingham is as close as it gets to putting a face on the controversial practice of "predictive policing." Over the past decade, the University of California-Los Angeles anthropology professor adapted his Pentagon-funded research in forecasting battlefield casualties in Iraq to predicting crime for American police departments, patenting his research and founding a for-profit company named PredPol, LLC. PredPol quickly became one of the market leaders in the nascent field of crime prediction around 2012, but also came under fire from activists and civil libertarians who argued the firm provided a sort of "tech-washing" for racially biased, ineffective policing methods. Now, Brantingham is using military research funding for another tech and policing collaboration with potentially damaging repercussions: using machine learning, the Los Angeles Police Department's criminal data, and an outdated gang territory map to automate the classification of "gang-related" crimes. Being classified as a gang member or related to a gang crime can result in additional criminal charges, heavier prison sentences, or inclusion in a civil gang injunction that restricts a person's movements and ability to associate with other people.

Real-time crime forecasting is important. However, accurate prediction of when and where the next crime will happen is difficult. No known physical model provides a reasonable approximation to such a complex system. Historical crime data are sparse in both space and time and the signal of interests is weak. In this work, we first present a proper representation of crime data. We then adapt the spatial temporal residual network on the well represented data to predict the distribution of crime in Los Angeles at the scale of hours in neighborhood-sized parcels. These experiments as well as comparisons with several existing approaches to prediction demonstrate the superiority of the proposed model in terms of accuracy. Finally, we present a ternarization technique to address the resource consumption issue for its deployment in real world. This work is an extension of our short conference proceeding paper [Wang et al, Arxiv 1707.03340]. Keywords: Crime representation, Spatial-temporal deep learning, Real-time forecasting, Ternarization. 1 Introduction Forecasting crime at hourly or even finer temporal scales in micro-geographic regions is an important scientific and practical problem. Anticipating where and when crime is most likely to occur creates novel opportunities to prevent crime.

Accurate real time crime prediction is a fundamental issue for public safety, but remains a challenging problem for the scientific community. Crime occurrences depend on many complex factors. Compared to many predictable events, crime is sparse. At different spatio-temporal scales, crime distributions display dramatically different patterns. These distributions are of very low regularity in both space and time. In this work, we adapt the state-of-the-art deep learning spatio-temporal predictor, ST-ResNet [Zhang et al, AAAI, 2017], to collectively predict crime distribution over the Los Angeles area. Our models are two staged. First, we preprocess the raw crime data. This includes regularization in both space and time to enhance predictable signals. Second, we adapt hierarchical structures of residual convolutional units to train multi-factor crime prediction models. Experiments over a half year period in Los Angeles reveal highly accurate predictive power of our models.