Forecasting murder within a population of probationers and parolees: a high stakes application of statistical learning

  title={Forecasting murder within a population of probationers and parolees: a high stakes application of statistical learning},
  author={Richard A. Berk and Lawrence W. Sherman and Geoffrey Carroll Barnes and Ellen Kurtz and Lindsay Ahlman},
  journal={Journal of the Royal Statistical Society: Series A (Statistics in Society)},
Summary.  Forecasts of future dangerousness are often used to inform the sentencing decisions of convicted offenders. For individuals who are sentenced to probation or paroled to community supervision, such forecasts affect the conditions under which they are to be supervised. The statistical criterion for these forecasts is commonly called recidivism, which is defined as a charge or conviction for any new offence, no matter how minor. Only rarely do such forecasts make distinctions on the… 
Balancing the Costs of Forecasting Errors in Parole Decisions
In this paper, ways to think about forecasting errors in parole decisions are reviewed, including how to properly address the consequences of the two kinds of forecasting errors, known more formally as false positives and false negatives.
Forecasts of Violence to Inform Sentencing Decisions
An enhanced version of classifications trees available in R, with some technical enhancements to improve tree stability, is applied to provide a prototype procedure for making forecasts of future dangerousness that could be used to inform sentencing decisions when machine learning is not practical.
Studying Parole in the “Spotlight”: Lessons from a Large American Jurisdiction
In September 2008 the Governor of Pennsylvania, USA, imposed a moratorium on all parole (early conditional) releases from the state prisons, which lasted until March 2009. As a political measure, the
Predicting Recidivism in Homicide Offenders Using Classification Tree Analysis
Given the severity of the crime and the lengthy sentences often accompanying convictions, homicide tends to be seen as the culminating event in a criminal career. In an attempt to better understand
The effects of sanction intensity on criminal conduct: A randomized low-intensity probation experiment
Probation is a well-established part of our criminal justice toolkit, but we know surprisingly little about the circumstances under which it is effective. Attempts to increase supervision intensity
Written evidence submitted by Durham Constabulary (ALG0041)
 Durham Constabulary is exploring an algorithmic forecasting tool which identifies a suspect’s future risk of offending in order to provide decision support to police custody officers to reduce
Forecasting Domestic Violence: A Machine Learning Approach to Help Inform Arraignment Decisions
Arguably the most important decision at an arraignment is whether to release an offender until the date of his or her next scheduled court appearance. Under the Bail Reform Act of 1984, threats to
The Role of Race in Forecasts of Violent Crime
This paper addresses the role of race in forecasts of failure on probation or parole. Failure is defined as committing a homicide or attempted homicide or being the victim of a homicide or an
Actuarial Sentencing: An “Unsettled” Proposition
This paper discusses the concerns associated with the introduction of, and increased reliance on, actuarial risk tools in sentencing in order to: (1) stimulate cross-disciplinary dialog and research
Developing the actuarial prediction of violent and sexual reoffending
This thesis aims to develop and improve the actuarial prediction of violent and sexual offending. It demonstrates the importance of understanding offence classification and specialisation, and the


Forecasting Dangerous Inmate Misconduct: An Application of Ensemble Statistical Procedures
In this paper, we attempt to forecast which prison inmates are likely to engage in very serious misconduct while incarcerated. Such misconduct would usually be a major felony if committed outside of
Predicting Individual Crime Rates
There are great individual differences between offenders in their crime rates. The chronic offenders who commit the most crimes tend to commit them at the highest rates. High individual crime rates
Factors for Predicting Parole Success
The writer has compiled a considerable weight of statistics on factors which might be considered as possible determinants of parole success, made with data at hand on two hundred and sixty-three consecutive paroles from a reformatory for young men.
Problems in Parole Prediction: A Historical Analysis
A review of past efforts to predict parole outcome indicates that, although there have been some recent improvements in the methodology, there has been no appreciable increase in predictive power.
Forecasting Methods in Crime and Justice
Researchers who study crime and justice have been forecasting a variety of outcomes for nearly a century. Perhaps the most well known are forecasts of behavior after release from prison. Other
Developing a Practical Forecasting Screener for Domestic Violence Incidents
In this article, the authors report on the development of a short screening tool that deputies in the Los Angeles Sheriff’s Department could use in the field to help forecast domestic violence
Fairness and effectiveness in policing : the evidence
Because police are the most visible face of government power for most citizens, they are expected to deal effectively with crime and disorder and to be impartial. Producing justice through the fair,
A Comparison of Alternative Methods of Parole Prediction
The purpose of the present paper is to compare the relative accuracy of these two methods as a basis for predicting behavior on parole.
Prediction: An Overview of Selected Methodological Issues
A variety of statistical methods are available for making criminal justice predictions. None possesses a clear-cut advantage over the others, and this may be due to the poor quality of available
The power few: experimental criminology and the reduction of harm
The promise of experimental criminology is finding ways to reduce harm from crime and injustice. The problem of experimental criminology is that so few experiments produce evidence of big effects