Browsing by Author "Carter, Jeremy"

Now showing 1 - 10 of 12
  • Thumbnail Image
    Item
    CDASH: Community Data Analytics for Social Harm Prevention
    (IEEE, 2018-09) Pandey, Saurabh; Chowdhury, Nahida; Patil, Milan; Raje, Rajeev R.; Shreyas, C. S.; Mohler, George; Carter, Jeremy; Computer and Information Science, School of Science
    Communities are adversely affected by heterogeneous social harm events (e.g., crime, traffic crashes, medical emergencies, drug use) and police, fire, health and social service departments are tasked with mitigating social harm through various types of interventions. Smart cities of the future will need to leverage IoT, data analytics, and government and community human resources to most effectively reduce social harm. Currently, methods for collection, analysis, and modeling of heterogeneous social harm data to identify government actions to improve quality of life are needed. In this paper we propose a system, CDASH, for synthesizing heterogeneous social harm data from multiples sources, identifying social harm risks in space and time, and communicating the risk to the relevant community resources best equipped to intervene. We discuss the design, architecture, and performance of CDASH. CDASH allows users to report live social harm events using mobile hand-held devices and web browsers and flags high risk areas for law enforcement and first responders. To validate the methodology, we run simulations on historical social harm event data in Indianapolis illustrating the advantages of CDASH over recently introduced social harm indices and existing point process methods used for predictive policing.
  • Thumbnail Image
    Item
    Enhancing Trust-based Data Analytics for Forecasting Social Harm
    (IEEE, 2020-09) Chowdhury, Nahida Sultana; Raje, Rajeev R.; Pandey, Saurabh; Mohler, George; Carter, Jeremy; School of Public and Environmental Affairs
    First responders deal with a variety of “social harm” events (e.g. crime, traffic crashes, medical emergencies) that result in physical, emotional, and/or financial hardships. Through data analytics, resources can be efficiently allocated to increase the impact of interventions aimed at reducing social harm -T-CDASH (Trusted Community Data Analytics for Social Harm) is an ongoing joint effort between the Indiana University Purdue University Indianapolis (IUPUI), the Indianapolis Metropolitan Police Department (IMPD), and the Indianapolis Emergency Medical Services (IEMS) with this goal of using data analytics to efficiently allocate resources to respond to and reduce social harm. In this paper, we make several enhancements to our previously introduced trust estimation framework T-CDASH. These enhancements include additional metrics for measuring the effectiveness of forecasts, evaluation on new datasets, and an incorporation of collaborative trust models. To empirically validate our current work, we ran simulations on newly collected 2019 and 2020 (Jan-April) social harm data from the Indianapolis metro area. We describe the behavior and significance of the collaboration and their comparison with previously introduced stand-alone models.
  • Thumbnail Image
    Item
    Impact of social distancing during COVID-19 pandemic on crime in Los Angeles and Indianapolis
    (Elsevier, 2020-05-01) Mohler, George; Bertozzi, Andrea L.; Carter, Jeremy; Short, Martin B.; Sledge, Daniel; Tita, George E.; Uchida, Craig D.; Brantingham, P. Jeffrey; Computer and Information Science, School of Science
    Governments have implemented social distancing measures to address the ongoing COVID-19 pandemic. The measures include instructions that individuals maintain social distance when in public, school closures, limitations on gatherings and business operations, and instructions to remain at home. Social distancing may have an impact on the volume and distribution of crime. Crimes such as residential burglary may decrease as a byproduct of increased guardianship over personal space and property. Crimes such as domestic violence may increase because of extended periods of contact between potential offenders and victims. Understanding the impact of social distancing on crime is critical for ensuring the safety of police and government capacity to deal with the evolving crisis. Understanding how social distancing policies impact crime may also provide insights into whether people are complying with public health measures. Examination of the most recently available data from both Los Angeles, CA, and Indianapolis, IN, shows that social distancing has had a statistically significant impact on a few specific crime types. However, the overall effect is notably less than might be expected given the scale of the disruption to social and economic life.
  • Thumbnail Image
    Item
    Improving social harm indices with a modulated Hawkes process
    (Elsevier, 2018-06) Mohler, George; Carter, Jeremy; Raje, Rajeev; Computer and Information Science, School of Science
    Communities are affected adversely by a range of social harm events, such as crime, traffic crashes, medical emergencies, and drug use. The police, fire, health and social service departments are tasked with mitigating such social harm through various types of interventions. While various different social harm indices have been proposed for allocating resources to spatially fixed hotspots, the risk of social harm events is dynamic, and new algorithms and software systems that are capable of quickly identifying risks and triggering appropriate public safety responses are needed. We propose a novel modulated Hawkes process for this purpose that offers flexible approaches to both (i) the incorporation of spatial covariates and leading indicators for variance reduction in the case of rarer event categories, and (ii) the capture of dynamic hotspot formation through self-excitation. We present an efficient l1-penalized EM algorithm for estimating the model that performs feature selection for the spatial covariates of each incident type simultaneously. We provide simulation results using data from the Indianapolis Metropolitan Police Department in order to illustrate the advantages of the modulated Hawkes process model of social harm over various recently introduced social harm indices and property crime Hawkes processes.
  • Thumbnail Image
    Item
    Learning to rank spatio-temporal event hotspots
    (BMC, 2020) Mohler, George; Porter, Michael; Carter, Jeremy; LaFree, Gary; Computer and Information Science, School of Science
    Background Crime, traffic accidents, terrorist attacks, and other space-time random events are unevenly distributed in space and time. In the case of crime, hotspot and other proactive policing programs aim to focus limited resources at the highest risk crime and social harm hotspots in a city. A crucial step in the implementation of these strategies is the construction of scoring models used to rank spatial hotspots. While these methods are evaluated by area normalized Recall@k (called the predictive accuracy index), models are typically trained via maximum likelihood or rules of thumb that may not prioritize model accuracy in the top k hotspots. Furthermore, current algorithms are defined on fixed grids that fail to capture risk patterns occurring in neighborhoods and on road networks with complex geometries. Results We introduce CrimeRank, a learning to rank boosting algorithm for determining a crime hotspot map that directly optimizes the percentage of crime captured by the top ranked hotspots. The method employs a floating grid combined with a greedy hotspot selection algorithm for accurately capturing spatial risk in complex geometries. We illustrate the performance using crime and traffic incident data provided by the Indianapolis Metropolitan Police Department, IED attacks in Iraq, and data from the 2017 NIJ Real-time crime forecasting challenge. Conclusion Our learning to rank strategy was the top performing solution (PAI metric) in the 2017 challenge. We show that CrimeRank achieves even greater gains when the competition rules are relaxed by removing the constraint that grid cells be a regular tessellation.
  • Thumbnail Image
    Item
    New Spatio-temporal Hawkes Process Models For Social Good
    (2022-05) Chiang, Wen-Hao; Mohler, George; Al Hasan, Mohammad; Dundar, Murat; Carter, Jeremy
    As more and more datasets with self-exciting properties become available, the demand for robust models that capture contagion across events is also getting stronger. Hawkes processes stand out given their ability to capture a wide range of contagion and self-excitation patterns, including the transmission of infectious disease, earthquake aftershock distributions, near-repeat crime patterns, and overdose clusters. The Hawkes process is flexible in modeling these various applications through parametric and non-parametric kernels that model event dependencies in space, time and on networks. In this thesis, we develop new frameworks that integrate Hawkes Process models with multi-armed bandit algorithms, high dimensional marks, and high-dimensional auxiliary data to solve problems in search and rescue, forecasting infectious disease, and early detection of overdose spikes. In Chapter 3, we develop a method applications to the crisis of increasing overdose mortality over the last decade. We first encode the molecular substructures found in a drug overdose toxicology report. We then cluster these overdose encodings into different overdose categories and model these categories with spatio-temporal multivariate Hawkes processes. Our results demonstrate that the proposed methodology can improve estimation of the magnitude of an overdose spike based on the substances found in an initial overdose. In Chapter 4, we build a framework for multi-armed bandit problems arising in event detection where the underlying process is self-exciting. We derive the expected number of events for Hawkes processes given a parametric model for the intensity and then analyze the regret bound of a Hawkes process UCB-normal algorithm. By introducing the Hawkes Processes modeling into the upper confidence bound construction, our models can detect more events of interest under the multi-armed bandit problem setting. We apply the Hawkes bandit model to spatio-temporal data on crime events and earthquake aftershocks. We show that the model can quickly learn to detect hotspot regions, when events are unobserved, while striking a balance between exploitation and exploration. In Chapter 5, we present a new spatio-temporal framework for integrating Hawkes processes with multi-armed bandit algorithms. Compared to the methods proposed in Chapter 4, the upper confidence bound is constructed through Bayesian estimation of a spatial Hawkes process to balance the trade-off between exploiting and exploring geographic regions. The model is validated through simulated datasets and real-world datasets such as flooding events and improvised explosive devices (IEDs) attack records. The experimental results show that our model outperforms baseline spatial MAB algorithms through rewards and ranking metrics. In Chapter 6, we demonstrate that the Hawkes process is a powerful tool to model the infectious disease transmission. We develop models using Hawkes processes with spatial-temporal covariates to forecast COVID-19 transmission at the county level. In the proposed framework, we show how to estimate the dynamic reproduction number of the virus within an EM algorithm through a regression on Google mobility indices. We also include demographic covariates as spatial information to enhance the accuracy. Such an approach is tested on both short-term and long-term forecasting tasks. The results show that the Hawkes process outperforms several benchmark models published in a public forecast repository. The model also provides insights on important covariates and mobility that impact COVID-19 transmission in the U.S. Finally, in chapter 7, we discuss implications of the research and future research directions.
  • Thumbnail Image
    Item
    A Penalized Likelihood Method for Balancing Accuracy and Fairness in Predictive Policing
    (IEEE, 2018-10) Mohler, George; Raje, Rajeev; Carter, Jeremy; Valasik, Matthew; Brantingham, P. Jeffrey; Computer and Information Science, School of Science
    Racial bias of predictive policing algorithms has been the focus of recent research and, in the case of Hawkes processes, feedback loops are possible where biased arrests are amplified through self-excitation, leading to hotspot formation and further arrests of minority populations. In this article we develop a penalized likelihood approach for introducing fairness into point process models of crime. In particular, we add a penalty term to the likelihood function that encourages the amount of police patrol received by each of several demographic groups to be proportional to the representation of that group in the total population. We apply our model to historical crime incident data in Indianapolis and measure the fairness and accuracy of the two approaches across several crime categories. We show that fairness can be introduced into point process models of crime so that patrol levels proportionally match demographics, though at a cost of reduced accuracy of the algorithms.
  • Thumbnail Image
    Item
    Point process modeling of drug overdoses with heterogeneous and missing data
    (Institute of Mathematical Statistics, 2021) Liu, Xueying; Carter, Jeremy; Ray, Brad; Mohler, George; Computer and Information Science, School of Science
    Opioid overdose rates have increased in the United States over the past decade and reflect a major public health crisis. Modeling and prediction of drug and opioid hotspots, where a high percentage of events fall in a small percentage of space–time, could help better focus limited social and health services. In this work we present a spatial-temporal point process model for drug overdose clustering. The data input into the model comes from two heterogeneous sources: (1) high volume emergency medical calls for service (EMS) records containing location and time but no information on the type of nonfatal overdose, and (2) fatal overdose toxicology reports from the coroner containing location and high-dimensional information from the toxicology screen on the drugs present at the time of death. We first use nonnegative matrix factorization to cluster toxicology reports into drug overdose categories, and we then develop an EM algorithm for integrating the two heterogeneous data sets, where the mark corresponding to overdose category is inferred for the EMS data and the high volume EMS data is used to more accurately predict drug overdose death hotspots. We apply the algorithm to drug overdose data from Indianapolis, showing that the point process defined on the integrated data out-performs point processes that use only coroner data (AUC improvement 0.81 to 0.85). We also investigate the extent to which overdoses are contagious, as a function of the type of overdose, while controlling for exogenous fluctuations in the background rate that might also contribute to clustering. We find that drug and opioid overdose deaths exhibit significant excitation with branching ratio ranging from 0.72 to 0.98.
  • Thumbnail Image
    Item
    Reducing Bias in Estimates for the Law of Crime Concentration
    (Springer, 2019) Mohler, George; Brantingham, P. Jeffrey; Carter, Jeremy; Short, Martin; Computer and Information Science, School of Science
    Objectives The law of crime concentration states that half of the cumulative crime in a city will occur within approximately 4% of the city’s geography. The law is demonstrated by counting the number of incidents in each of N spatial areas (street segments or grid cells) and then computing a parameter based on the counts, such as a point estimate on the Lorenz curve or the Gini index. Here we show that estimators commonly used in the literature for these statistics are biased when the number of incidents is low (several thousand or less). Our objective is to significantly reduce bias in estimators for the law of crime concentration. Methods By modeling crime counts as a negative binomial, we show how to compute an improved estimate of the law of crime concentration at low event counts that significantly reduces bias. In particular, we use the Poisson–Gamma representation of the negative binomial and compute the concentration statistic via integrals for the Lorenz curve and Gini index of the inferred continuous Gamma distribution. Results We illustrate the Poisson–Gamma method with synthetic data along with homicide data from Chicago. We show that our estimator significantly reduces bias and is able to recover the true law of crime concentration with only several hundred events. Conclusions The Poisson–Gamma method has applications to measuring the concentration of rare events, comparisons of concentration across cities of different sizes, and improving time series estimates of crime concentration.
  • Thumbnail Image
    Item
    Rewiring Police Officer Training Networks to Reduce Forecasted Use of Force
    (ACM, 2023) Pandey, Ritika; Carter, Jeremy; Hill, James; Mohler, George; School of Public and Environmental Affairs
    Research has shown that police officer involved shootings, misconduct and excessive use of force complaints exhibit network effects, where officers are at greater risk of being involved in these incidents when they socialize with officers who have a history of use of force and misconduct. In this work, we first construct a network survival model for the time-to-event of use of force incidents involving new police trainees. The model includes network effects of the diffusion of risk from field training officer (FTO) to trainee. We then introduce a network rewiring algorithm to maximize the expected time to use of force events upon completion of field training. We study several versions of the algorithm, including constraints that encourage demographic diversity of FTOs. Using data from Indianapolis, we show that rewiring the network can increase the expected time (in days) of a recruit's first use of force incident by 8%. We then discuss the potential benefits and challenges associated with implementing such an algorithm in practice.