Fair and Effective Policing for Neighborhood Safety: Understanding and Overcoming Selection Biases

An accurate crime prediction and risk estimation can help improve the efficiency and effectiveness of policing activities. However, reports have revealed that biases like racial prejudice could exist in policing enforcement, and trained predictors may inherit them. In this work, we study the possibl...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Weijeiying Ren, Kunpeng Liu, Tianxiang Zhao , Yanjie Fu 
Formato: article
Lenguaje:EN
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://doaj.org/article/276b831788b747ab8623b025217025f2
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:276b831788b747ab8623b025217025f2
record_format dspace
spelling oai:doaj.org-article:276b831788b747ab8623b025217025f22021-11-30T18:30:56ZFair and Effective Policing for Neighborhood Safety: Understanding and Overcoming Selection Biases2624-909X10.3389/fdata.2021.787459https://doaj.org/article/276b831788b747ab8623b025217025f22021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fdata.2021.787459/fullhttps://doaj.org/toc/2624-909XAn accurate crime prediction and risk estimation can help improve the efficiency and effectiveness of policing activities. However, reports have revealed that biases like racial prejudice could exist in policing enforcement, and trained predictors may inherit them. In this work, we study the possible reasons and countermeasures to this problem, using records from the New York frisk and search program (NYCSF) as the dataset. Concretely, we provide analysis on the possible origin of this phenomenon from the perspective of risk discrepancy, and study it with the scope of selection bias. Motivated by theories in causal inference, we propose a re-weighting approach based on propensity score to balance the data distribution, with respect to the identified treatment: search action. Naively applying existing re-weighting approaches in causal inference is not suitable as the weight is passively estimated from observational data. Inspired by adversarial learning techniques, we formulate the predictor training and re-weighting as a min-max game, so that the re-weighting scale can be automatically learned. Specifically, the proposed approach aims to train a model that: 1) able to balance the data distribution in the searched and un-searched groups; 2) remain discriminative between treatment interventions. Extensive evaluations on real-world dataset are conducted, and results validate the effectiveness of the proposed framework.Weijeiying RenKunpeng LiuTianxiang Zhao Yanjie Fu Frontiers Media S.A.articlecounterfactual learningneighborhood safetyfairnessstop-and-friskadversarial learningInformation technologyT58.5-58.64ENFrontiers in Big Data, Vol 4 (2021)
institution DOAJ
collection DOAJ
language EN
topic counterfactual learning
neighborhood safety
fairness
stop-and-frisk
adversarial learning
Information technology
T58.5-58.64
spellingShingle counterfactual learning
neighborhood safety
fairness
stop-and-frisk
adversarial learning
Information technology
T58.5-58.64
Weijeiying Ren
Kunpeng Liu
Tianxiang Zhao 
Yanjie Fu 
Fair and Effective Policing for Neighborhood Safety: Understanding and Overcoming Selection Biases
description An accurate crime prediction and risk estimation can help improve the efficiency and effectiveness of policing activities. However, reports have revealed that biases like racial prejudice could exist in policing enforcement, and trained predictors may inherit them. In this work, we study the possible reasons and countermeasures to this problem, using records from the New York frisk and search program (NYCSF) as the dataset. Concretely, we provide analysis on the possible origin of this phenomenon from the perspective of risk discrepancy, and study it with the scope of selection bias. Motivated by theories in causal inference, we propose a re-weighting approach based on propensity score to balance the data distribution, with respect to the identified treatment: search action. Naively applying existing re-weighting approaches in causal inference is not suitable as the weight is passively estimated from observational data. Inspired by adversarial learning techniques, we formulate the predictor training and re-weighting as a min-max game, so that the re-weighting scale can be automatically learned. Specifically, the proposed approach aims to train a model that: 1) able to balance the data distribution in the searched and un-searched groups; 2) remain discriminative between treatment interventions. Extensive evaluations on real-world dataset are conducted, and results validate the effectiveness of the proposed framework.
format article
author Weijeiying Ren
Kunpeng Liu
Tianxiang Zhao 
Yanjie Fu 
author_facet Weijeiying Ren
Kunpeng Liu
Tianxiang Zhao 
Yanjie Fu 
author_sort Weijeiying Ren
title Fair and Effective Policing for Neighborhood Safety: Understanding and Overcoming Selection Biases
title_short Fair and Effective Policing for Neighborhood Safety: Understanding and Overcoming Selection Biases
title_full Fair and Effective Policing for Neighborhood Safety: Understanding and Overcoming Selection Biases
title_fullStr Fair and Effective Policing for Neighborhood Safety: Understanding and Overcoming Selection Biases
title_full_unstemmed Fair and Effective Policing for Neighborhood Safety: Understanding and Overcoming Selection Biases
title_sort fair and effective policing for neighborhood safety: understanding and overcoming selection biases
publisher Frontiers Media S.A.
publishDate 2021
url https://doaj.org/article/276b831788b747ab8623b025217025f2
work_keys_str_mv AT weijeiyingren fairandeffectivepolicingforneighborhoodsafetyunderstandingandovercomingselectionbiases
AT kunpengliu fairandeffectivepolicingforneighborhoodsafetyunderstandingandovercomingselectionbiases
AT tianxiangzhao fairandeffectivepolicingforneighborhoodsafetyunderstandingandovercomingselectionbiases
AT yanjiefu fairandeffectivepolicingforneighborhoodsafetyunderstandingandovercomingselectionbiases
_version_ 1718406368189218816