Learning to Detect Patterns of Crime
By Tongyuan Wang, Cynthia Rudin, Daniel Wagner, Rich Sevieri. 2013
177 citations recorded by the source corpus.
Our goal is to automatically detect patterns of crime. Among a large set of crimes that happen every year in a major city, it is challenging, time-consuming, and labor-intensive for crime analysts to determine which ones may have been committed by the same individual(s). If automated, data-driven tools for crime pattern detection are made available to assist analysts, these tools could help police to better understand patterns of crime, leading to more precise attribution of past crimes, and the apprehension of suspects. To do this, we propose a pattern detection algorithm called Series Finder, that grows a pattern of discovered crimes from within a database, starting from a "seed" of a few crimes. Series Finder incorporates both the common characteristics of all patterns and the unique aspects of each specific pattern, and has had promising results on a decade's worth of crime pattern data collected by the Crime Analysis Unit of the Cambridge Police Department.
Subfields: Artificial Intelligence, Information Systems, Sociology and Political Science, Anomaly & Outlier Detection
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Aaron Roth
- Zhiwei Steven Wu
- Michael Kearns
- Seth Neel
- Matthew Joseph
- Jamie H. Morgenstern
- Jonathan Ullman
- Shahin Jabbari
In Information Systems
- Matthew Joseph
- Anil Jayanti Aswani
- Jamie H. Morgenstern
- Andreas Krause
- Nuria Oliver
- Sina Aghaei
- Aaron Roth
- Alex Pentland
In Sociology and Political Science
- Aaron Roth
- Michael Kearns
- Zhiwei Steven Wu
- Seth Neel
- Sina Aghaei
- Phebe Vayanos
- Hoda Heidari
- Shahin Jabbari
In Anomaly & Outlier Detection
Citations in the corpus
- Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness (2017, background): “As machine learning is being deployed in increasingly consequential domains (including policing (Rudin, 2013), criminal sentencing (Barry-Jester et al.”
- Learning Optimal and Fair Decision Trees for Non-Discriminative Decision-Making (2019, background): “For example, they can help inform the decision to give access to credit, benefits, or public services (Byrnes 2016), they can help support criminal sentencing decisions (Rudin 2013), and assist screening decisions for jobs/college admissions (Miller 2015).”
- A Convex Framework for Fair Regression (2017, background): “…consequential decisions about individual citizens (including in domains such as credit, employment, education and criminal sentencing [3, 4, 26, 29]) has been accompanied by increased reports of instances in which the algorithms and models employed can be unfair or discriminatory in a variety…”
- Fairness in Learning: Classic and Contextual Bandits (2016, methodology): “Automated techniques from statistics and machine learning are increasingly being used to make decisions that have important consequences on people’s lives, including hiring [Miller, 2015], lending [Byrnes, 2016], policing [Rudin, 2013], and even criminal sentencing [Barry-Jester et al., 2015].”
- Fairness in Reinforcement Learning (2016, background): “In settings as diverse as policing [22], hiring [19], lending [4], and criminal sentencing [2], mounting empirical evidence suggests these concerns are not merely hypothetical [1, 25].”
- Convex Formulations for Fair Principal Component Analysis (2018, background): “…success of machine learning in informing policies and automating decision-making, there is growing concern about the fairness (with respect to protected classes like race or gender) of the resulting policies and decisions (Miller 2015; Rudin 2013; Angwin et al. 2016; Munoz, Smith, and Patil 2016).”
- The Tyranny of Data? The Bright and Dark Sides of Data-Driven Decision-Making for Social Good (2016, methodology): “The people-centric perspective has mostly been used for individual or collective criminal profiling [67, 72, 91].”
- Accountability of AI Under the Law: The Role of Explanation (2017, unknown): “AI systems are currently used in applications ranging from automatic face-focus on cameras [Ray and Nicpon-ski, 2005] and predictive policing [Wang et al., 2013] to segmenting MRI scans [Aibinu et al., 2008] and language translation [Chand, 2016].”
- Once Upon a Crime: Towards Crime Prediction from Demographics and Mobile Data (2014, background): “Wang et al. [42] proposed Series Finder , a machine learning approach to the problem of detecting specific patterns in crimes that are committed by the same offender or group of offenders.”
- Fair, Transparent, and Accountable Algorithmic Decision-making Processes (2017, background): “Many decisions with significant individual and societal implications previously made by humans alone –often by experts– are now made or assisted by algorithms, including hiring [12], lending [34], policing [66], criminal sentencing [5], and stock trading [33].”
- Fairness Behind a Veil of Ignorance: A Welfare Analysis for Automated Decision Making (2018, background): “, 2017], policing [Rudin, 2013], and criminal justice [Barry-Jester et al.”
- Rawlsian Fairness for Machine Learning (2016, background): “Automated techniques from statistics and machine learning are increasingly being used to make important decisions that directly affect the lives of individuals, including hiring [25], lending [8], policing [30], and criminal sentencing [6].”