Skip to main navigation Skip to search Skip to main content

Comparing Conventional and Machine-Learning Approaches to Risk Assessment in Domestic Abuse Cases

  • Jeffrey Grogger*
  • , Sean Gupta
  • , Ria Ivandic
  • , Tom Kirchmaier
  • *Corresponding author for this work
  • University of Chicago
  • Sensyne Health
  • London School of Economics and Political Science

Research output: Contribution to journal › Journal article › Research › peer-review

Abstract

We compare predictions from a conventional protocol-based approach to risk assessment with those based on a machine-learning approach. We first show that the conventional predictions are less accurate than, and have similar rates of negative prediction error as, a simple Bayes classifier that makes use of only the base failure rate. Machine-learning algorithms based on the underlying risk assessment questionnaire do better under the assumption that negative prediction errors are more costly than positive prediction errors. Machine-learning models based on two-year criminal histories do even better. Indeed, adding the protocol-based features to the criminal histories adds little to the predictive adequacy of the model. We suggest using the predictions based on criminal histories to prioritize incoming calls for service, and devising a more sensitive instrument to distinguish true from false positives that result from this initial screening.

Original languageEnglish
JournalJournal of Empirical Legal Studies
Volume18
Issue number1
Pages (from-to)90-130
Number of pages41
ISSN1740-1453
DOIs
Publication statusPublished - Mar 2021
Externally publishedYes

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

  1. SDG 16 - Peace, Justice and Strong Institutions
    SDG 16 Peace, Justice and Strong Institutions

Cite this