A machine learning analysis of misconduct in the New York Police Department

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Timothy I.C. Cubitt ◽  
Philip Birch
Keyword(s):  
Machine Learning ◽  
New York ◽  
Police Officers ◽  
Police Department ◽  
Police Misconduct ◽  
Prevention Policy ◽  
Policy And Practice ◽  
Data Set ◽  
Content Type ◽  
New York Police Department

PurposeThere is a paucity of data available relating to the misconduct of police officers in larger policing agencies, typically resulting in case study approaches and limited insight into the factors associated with serious misconduct. This paper seeks to contribute to the emerging knowledge base on police misconduct through analysis of 28,429 complaints among 3,830 officers in the New York Police Department, between 2000 and 2019.Design/methodology/approachThis study utilized a data set consisting of officer and complainant demographics, and officer complaint records. Machine learning analytics were employed, specifically random forest, to consider which variables were most associated with serious misconduct among officers that committed misconduct. Partial dependence plots were employed among variables identified as important to consider the points at which misconduct was most, and least likely to occur.FindingsPrior instances of serious misconduct were particularly associated with further instances of serious misconduct, while remedial action did not appear to have an impact in preventing further misconduct. Inexperience, both in rank and age, was associated with misconduct. Specific prior complaints, such as minor use of force, did not appear to be particularly associated with instances of serious misconduct. The characteristics of the complainant held more importance than the characteristics of the officer.Originality/valueThe ability to analyze a data set of this size is unusual and important to progressing the knowledge area regarding police misconduct. This study contributes to the growing use of machine learning in understanding the police misconduct environment, and more accurately tailoring misconduct prevention policy and practice.

Shift work and overtime across a career in law enforcement: a 15-year study

2021 ◽  
Vol 44 (2) ◽  
pp. 200-212
Author(s):  
Samantha M. Riedy ◽  
Desta Fekedulegn ◽  
Bryan Vila ◽  
Michael Andrew ◽  
John M. Violanti
Keyword(s):  
New York ◽  
Law Enforcement ◽  
Shift Work ◽  
Police Officers ◽  
Night Shift ◽  
Police Department ◽  
Work Hours ◽  
Negative Effects ◽  
Content Type ◽  
Long Work Hours

PurposeTo characterize changes in work hours across a career in law enforcement.Design/methodology/approachN = 113 police officers enrolled in the BCOPS cohort were studied. The police officers started their careers in law enforcement between 1994 and 2001 at a mid-sized, unionized police department in northwestern New York and continued to work at this police department for at least 15 years. Day-by-day work history records were obtained from the payroll department. Work hours, leave hours and other pay types were summarized for each calendar year across their first 15 years of employment. Linear mixed-effects models with a random intercept over subject were used to determine if there were significant changes in pay types over time.FindingsA total of 1,617 individual-years of data were analyzed. As the police officers gained seniority at the department, they worked fewer hours and fewer night shifts. Total paid hours did not significantly change due to seniority-based increases in vacation time. Night shift work was increasingly in the form of overtime as officers gained seniority. Overtime was more prevalent at the beginning of a career and after a promotion from police officer to detective.Originality/valueShiftwork and long work hours have negative effects on sleep and increase the likelihood of on-duty fatigue and performance impairment. The results suggest that there are different points within a career in law enforcement where issues surrounding shiftwork and long work hours may be more prevalent. This has important implications for predicting fatigue, developing effective countermeasures and measuring fatigue-related costs.

The onset of police misconduct

2014 ◽  
Vol 37 (2) ◽  
pp. 285-304 ◽  
Author(s):  
Christopher Harris
Keyword(s):  
Military Service ◽  
Design Methodology ◽  
Police Department ◽  
Future Research ◽  
Police Misconduct ◽  
Substantial Portion ◽  
Data Set ◽  
Content Type ◽  
Practical Implications ◽  
Over Time

Purpose – The purpose of this paper is to investigate the factors which contribute to, or mitigate against, both the likelihood and timing of the onset of police misconduct. Design/methodology/approach – Research hypotheses were tested examining the first personnel complaint filed against officers, using both all complaints and only substantiated complaints, from data collected on a large cohort of officers followed over a substantial portion of their careers. Findings – Black officers and those exhibiting poor academy performance were at an increased likelihood of onset when compared to white and Hispanic officers and those who did better in the academy, while having a college degree lowered this likelihood. Officers whose first complaints were filed by citizens, and officers working certain patrol zones had quicker onset times. Those officers whose first complaint was related to service, as well as officers with prior military service, had longer onset times. Research limitations/implications – This study relies on personnel complaints to measure onset, was conducted in a very large police department, and does not include arrest data on officers over time. Practical implications – Onset occurs early in officers’ careers. Some factors are consistent across complaint types, while others depend on whether all complaints or only substantiated complaints are used to measure onset, which suggests that future research should consider carefully which measure they employ. Originality/value – This study employs a longitudinal data set which follows a cohort of officers from the start of their careers, and is thus ideal for exploring the onset of misconduct.

scholarly journals Police Misconduct, Community Opposition, and Urban Governance in New York City, 1945–1965

2015 ◽  
Vol 44 (4) ◽  
pp. 643-668 ◽  
Author(s):  
Themis Chronopoulos
Keyword(s):  
New York ◽  
New York City ◽  
World War Ii ◽  
York City ◽  
Urban Governance ◽  
Police Department ◽  
Police Misconduct ◽  
World War ◽  
Police Reform ◽  
Black Freedom

In the post–World War II period, the police department emerged as one of the most problematic municipal agencies in New York City. Patrolmen and their superiors did not pay much attention to crime; instead they looked the other way, received payoffs from organized crime, performed haphazardly, and tolerated conditions that were unacceptable in a modern city with global ambitions. At the same time, patrolmen demanded deference and respect from African American civilians and routinely demeaned and brutalized individuals who appeared to be challenging their authority. The antagonism between African Americans and the New York Police Department (NYPD) intensified as local and national black freedom organizations paid more attention to police behavior and made police reform one of their main goals.

A systematic review of machine learning-based missing value imputation techniques

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Tressy Thomas ◽  
Enayat Rajabi
Keyword(s):  
Machine Learning ◽  
Selection Process ◽  
Evaluation Metrics ◽  
Correct Prediction ◽  
Data Sets ◽  
Data Set ◽  
Missing Value ◽  
Content Type ◽  
Missing Value Imputation ◽  
Literature Reviews

PurposeThe primary aim of this study is to review the studies from different dimensions including type of methods, experimentation setup and evaluation metrics used in the novel approaches proposed for data imputation, particularly in the machine learning (ML) area. This ultimately provides an understanding about how well the proposed framework is evaluated and what type and ratio of missingness are addressed in the proposals. The review questions in this study are (1) what are the ML-based imputation methods studied and proposed during 2010–2020? (2) How the experimentation setup, characteristics of data sets and missingness are employed in these studies? (3) What metrics were used for the evaluation of imputation method?Design/methodology/approachThe review process went through the standard identification, screening and selection process. The initial search on electronic databases for missing value imputation (MVI) based on ML algorithms returned a large number of papers totaling at 2,883. Most of the papers at this stage were not exactly an MVI technique relevant to this study. The literature reviews are first scanned in the title for relevancy, and 306 literature reviews were identified as appropriate. Upon reviewing the abstract text, 151 literature reviews that are not eligible for this study are dropped. This resulted in 155 research papers suitable for full-text review. From this, 117 papers are used in assessment of the review questions.FindingsThis study shows that clustering- and instance-based algorithms are the most proposed MVI methods. Percentage of correct prediction (PCP) and root mean square error (RMSE) are most used evaluation metrics in these studies. For experimentation, majority of the studies sourced the data sets from publicly available data set repositories. A common approach is that the complete data set is set as baseline to evaluate the effectiveness of imputation on the test data sets with artificially induced missingness. The data set size and missingness ratio varied across the experimentations, while missing datatype and mechanism are pertaining to the capability of imputation. Computational expense is a concern, and experimentation using large data sets appears to be a challenge.Originality/valueIt is understood from the review that there is no single universal solution to missing data problem. Variants of ML approaches work well with the missingness based on the characteristics of the data set. Most of the methods reviewed lack generalization with regard to applicability. Another concern related to applicability is the complexity of the formulation and implementation of the algorithm. Imputations based on k-nearest neighbors (kNN) and clustering algorithms which are simple and easy to implement make it popular across various domains.

Different firm responses to the COVID-19 pandemic shocks: machine-learning evidence on the Vietnamese labor market

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Lam Hoang Viet Le ◽  
Toan Luu Duc Huynh ◽  
Bryan S. Weber ◽  
Bao Khac Quoc Nguyen
Keyword(s):  
Machine Learning ◽  
Labor Market ◽  
Large Scale ◽  
Government Support ◽  
Policy Implications ◽  
Machine Learning Techniques ◽  
Firm Characteristics ◽  
Data Set ◽  
Content Type ◽  
Firm Responses

PurposeThis paper aims to identify the disproportionate impacts of the COVID-19 pandemic on labor markets.Design/methodology/approachThe authors conduct a large-scale survey on 16,000 firms from 82 industries in Ho Chi Minh City, Vietnam, and analyze the data set by using different machine-learning methods.FindingsFirst, job loss and reduction in state-owned enterprises have been significantly larger than in other types of organizations. Second, employees of foreign direct investment enterprises suffer a significantly lower labor income than those of other groups. Third, the adverse effects of the COVID-19 pandemic on the labor market are heterogeneous across industries and geographies. Finally, firms with high revenue in 2019 are more likely to adopt preventive measures, including the reduction of labor forces. The authors also find a significant correlation between firms' revenue and labor reduction as traditional econometrics and machine-learning techniques suggest.Originality/valueThis study has two main policy implications. First, although government support through taxes has been provided, the authors highlight evidence that there may be some additional benefit from targeting firms that have characteristics associated with layoffs or other negative labor responses. Second, the authors provide information that shows which firm characteristics are associated with particular labor market responses such as layoffs, which may help target stimulus packages. Although the COVID-19 pandemic affects most industries and occupations, heterogeneous firm responses suggest that there could be several varieties of targeted policies-targeting firms that are likely to reduce labor forces or firms likely to face reduced revenue. In this paper, the authors outline several industries and firm characteristics which appear to more directly be reducing employee counts or having negative labor responses which may lead to more cost–effect stimulus.

scholarly journals On self-neglect and safeguarding adult reviews: diminishing returns or adding value?

2017 ◽  
Vol 19 (2) ◽  
pp. 53-66 ◽  
Author(s):  
Michael Preston-Shoot
Keyword(s):  
Thematic Analysis ◽  
Annual Reports ◽  
National Database ◽  
Service Improvement ◽  
Policy And Practice ◽  
Data Set ◽  
Content Type ◽  
Core Data ◽  
The Core

Purpose The purpose of this paper is twofold: first, to update the core data set of self-neglect serious case reviews (SCRs) and safeguarding adult reviews (SARs), and accompanying thematic analysis; second, to respond to the critique in the Wood Report of SCRs commissioned by Local Safeguarding Children Boards (LSCBs) by exploring the degree to which the reviews scrutinised here can transform and improve the quality of adult safeguarding practice. Design/methodology/approach Further published reviews are added to the core data set from the websites of Safeguarding Adults Boards (SABs) and from contacts with SAB independent chairs and business managers. Thematic analysis is updated using the four domains employed previously. The findings are then further used to respond to the critique in the Wood Report of SCRs commissioned by LSCBs, with implications discussed for Safeguarding Adult Boards. Findings Thematic analysis within and recommendations from reviews have tended to focus on the micro context, namely, what takes place between individual practitioners, their teams and adults who self-neglect. This level of analysis enables an understanding of local geography. However, there are other wider systems that impact on and influence this work. If review findings and recommendations are to fully answer the question “why”, systemic analysis should appreciate the influence of national geography. Review findings and recommendations may also be used to contest the critique of reviews, namely, that they fail to engage practitioners, are insufficiently systemic and of variable quality, and generate repetitive findings from which lessons are not learned. Research limitations/implications There is still no national database of reviews commissioned by SABs so the data set reported here might be incomplete. The Care Act 2014 does not require publication of reports but only a summary of findings and recommendations in SAB annual reports. This makes learning for service improvement challenging. Reading the reviews reported here against the strands in the critique of SCRs enables conclusions to be reached about their potential to transform adult safeguarding policy and practice. Practical implications Answering the question “why” is a significant challenge for SARs. Different approaches have been recommended, some rooted in systems theory. The critique of SCRs challenges those now engaged in SARs to reflect on how transformational change can be achieved to improve the quality of adult safeguarding policy and practice. Originality/value The paper extends the thematic analysis of available reviews that focus on work with adults who self-neglect, further building on the evidence base for practice. The paper also contributes new perspectives to the process of conducting SARs by using the analysis of themes and recommendations within this data set to evaluate the critique that reviews are insufficiently systemic, fail to engage those involved in reviewed cases and in their repetitive conclusions demonstrate that lessons are not being learned.

scholarly journals Aggressive Policing and the Educational Performance of Minority Youth

2018 ◽  
Author(s):  
Joscha Legewie ◽  
Jeffrey Fagan
Keyword(s):  
New York ◽  
African American ◽  
Police Officers ◽  
Social Life ◽  
Minority Groups ◽  
Police Department ◽  
Minority Youth ◽  
Educational Performance ◽  
High Crime ◽  
The Impact

An increasing number of minority youth experience contact with the criminal justice system. But how does the expansion of police presence in poor urban communities affect educational outcomes? Previous research points at multiple mechanisms with opposing effects. This article presents the first causal evidence of the impact of aggressive policing on minority youths’ educational performance. Under Operation Impact, the New York Police Department (NYPD) saturated high-crime areas with additional police officers with the mission to engage in aggressive, order-maintenance policing. To estimate the effect of this policing program, we use administrative data from more than 250,000 adolescents age 9 to 15 and a difference-in-differences approach based on variation in the timing of police surges across neighborhoods. We find that exposure to police surges significantly reduced test scores for African American boys, consistent with their greater exposure to policing. The size of the effect increases with age, but there is no discernible effect for African American girls and Hispanic students. Aggressive policing can thus lower educational performance for some minority groups. These findings provide evidence that the consequences of policing extend into key domains of social life, with implications for the educational trajectories of minority youth and social inequality more broadly.

Early prediction of chronic disease using an efficient machine learning algorithm through adaptive probabilistic divergence based feature selection approach

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Sandeepkumar Hegde ◽  
Monica R. Mundada
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Chronic Disease ◽  
Learning Algorithm ◽  
Predictive Ability ◽  
Experimental Result ◽  
Data Set ◽  
Content Type ◽  
Learning Classifier ◽  
Feature Selection Approach

Purpose According to the World Health Organization, by 2025, the contribution of chronic disease is expected to rise by 73% compared to all deaths and it is considered as global burden of disease with a rate of 60%. These diseases persist for a longer duration of time, which are almost incurable and can only be controlled. Cardiovascular disease, chronic kidney disease (CKD) and diabetes mellitus are considered as three major chronic diseases that will increase the risk among the adults, as they get older. CKD is considered a major disease among all these chronic diseases, which will increase the risk among the adults as they get older. Overall 10% of the population of the world is affected by CKD and it is likely to double in the year 2030. The paper aims to propose novel feature selection approach in combination with the machine-learning algorithm which can early predict the chronic disease with utmost accuracy. Hence, a novel feature selection adaptive probabilistic divergence-based feature selection (APDFS) algorithm is proposed in combination with the hyper-parameterized logistic regression model (HLRM) for the early prediction of chronic disease. Design/methodology/approach A novel feature selection APDFS algorithm is proposed which explicitly handles the feature associated with the class label by relevance and redundancy analysis. The algorithm applies the statistical divergence-based information theory to identify the relationship between the distant features of the chronic disease data set. The data set required to experiment is obtained from several medical labs and hospitals in India. The HLRM is used as a machine-learning classifier. The predictive ability of the framework is compared with the various algorithm and also with the various chronic disease data set. The experimental result illustrates that the proposed framework is efficient and achieved competitive results compared to the existing work in most of the cases. Findings The performance of the proposed framework is validated by using the metric such as recall, precision, F1 measure and ROC. The predictive performance of the proposed framework is analyzed by passing the data set belongs to various chronic disease such as CKD, diabetes and heart disease. The diagnostic ability of the proposed approach is demonstrated by comparing its result with existing algorithms. The experimental figures illustrated that the proposed framework performed exceptionally well in prior prediction of CKD disease with an accuracy of 91.6. Originality/value The capability of the machine learning algorithms depends on feature selection (FS) algorithms in identifying the relevant traits from the data set, which impact the predictive result. It is considered as a process of choosing the relevant features from the data set by removing redundant and irrelevant features. Although there are many approaches that have been already proposed toward this objective, they are computationally complex because of the strategy of following a one-step scheme in selecting the features. In this paper, a novel feature selection APDFS algorithm is proposed which explicitly handles the feature associated with the class label by relevance and redundancy analysis. The proposed algorithm handles the process of feature selection in two separate indices. Hence, the computational complexity of the algorithm is reduced to O(nk+1). The algorithm applies the statistical divergence-based information theory to identify the relationship between the distant features of the chronic disease data set. The data set required to experiment is obtained from several medical labs and hospitals of karkala taluk ,India. The HLRM is used as a machine learning classifier. The predictive ability of the framework is compared with the various algorithm and also with the various chronic disease data set. The experimental result illustrates that the proposed framework is efficient and achieved competitive results are compared to the existing work in most of the cases.

Consent searches: understanding the role of race and what occurs during the traffic stop

2019 ◽  
Vol 42 (4) ◽  
pp. 611-623
Author(s):  
Anthony G. Vito ◽  
Elizabeth L. Grossi ◽  
Vanessa Woodward Griffin ◽  
George E. Higgins
Keyword(s):  
Decision Making ◽  
Police Officer ◽  
Police Officers ◽  
Racial Profiling ◽  
Police Department ◽  
Theoretical Explanation ◽  
Cross Sectional ◽  
Content Type ◽  
Focal Concerns ◽  
Focal Concerns Theory

Purpose The purpose of this paper is to apply focal concerns theory as a theoretical explanation for police officer decision making during a traffic stop that results in a consent search. The study uses coefficients testing to better examine the issue of racial profiling through the use of a race-specific model. Design/methodology/approach The data for this study come from traffic stops conducted by the Louisville Police Department between January 1 and December 31, 2002. Findings The results show that the three components of focal concerns theory can explain police officer decision making for consent searches. Yet, the components of focal concerns theory play a greater role in stops of Caucasian male drivers. Research limitations/implications The data for this study are cross-sectional and self-reported from police officers. Practical implications This paper shows the utility of applying focal concerns theory as a theoretical explanation for police officer decision making on consent searches and how the effects of focal concerns vary depending on driver race. Social implications The findings based on focal concerns theory can provide an opportunity for police officers or departments to explain what factors impact the decision making during consent searches. Originality/value This is the first study (to the researchers’ knowledge) that examines the racial effects of focal concerns on traffic stop consent searchers using coefficients testing.

Sign in / Sign up

Export Citation Format

Share Document