Modelling underreported spatio-temporal crime events

Review Ergonomics

A Review of Incident Prediction, Resource Allocation, and Dispatch Models for Emergency Management

Ayan Mukhopadhyay et al.

Summary: In the past fifty years, researchers have developed various statistical, data-driven, analytical, and algorithmic approaches for designing and improving emergency response management systems. This survey provides a detailed review of these approaches, focusing on the key challenges and issues in incident prediction, incident detection, resource allocation, and computer-aided dispatch. It highlights the strengths and weaknesses of prior work and explores the similarities and differences between different modeling paradigms. The survey concludes by discussing open challenges and opportunities for future research in this complex domain.

ACCIDENT ANALYSIS AND PREVENTION (2022)

添加到收藏夹

Article Criminology & Penology

Estimating Crime in Place: Moving Beyond Residence Location

Alexandru Cernat et al.

Summary: Asking victims about the places where crimes happen leads to estimates of crime in place with better measurement properties, showing high similarity to police-recorded crime statistics. The survey-based offense location estimates have comparable reliability and validity to victim residence measures, suggesting their potential in improving crime estimation. However, estimates of crimes reported to the police show better validity but lower reliability and capture fewer crimes.

CRIME & DELINQUENCY (2022)

添加到收藏夹

Proceedings Paper Computer Science, Information Systems

Combinatorial Multi-armed Bandits for Resource Allocation

Jinhang Zuo et al.

Summary: The study focuses on the sequential resource allocation problem, where a decision maker needs to allocate budgets between resources to maximize expected rewards or minimize regret. The decision maker learns the value of allocating resources to each user through feedback on each user's received reward, assuming each user's reward follows an initially unknown random process. Combinatorial multi-armed bandit algorithms are designed to solve this problem with discrete or continuous budgets, achieving logarithmic regrets under semi-bandit feedback.

2021 55TH ANNUAL CONFERENCE ON INFORMATION SCIENCES AND SYSTEMS (CISS) (2021)

添加到收藏夹

Article Criminology & Penology

MEASURING THE DARK FIGURE OF CRIME IN GEOGRAPHIC AREAS: SMALL AREA ESTIMATION FROM THE CRIME SURVEY FOR ENGLAND AND WALES

David Buil-Gil et al.

Summary: Criminologists have long been aware of the impact of the "dark figure" of crime in police records on crime prevention strategies, and have used crime surveys to mitigate biases in police data. This paper uses crime survey data to produce small area estimates of crimes unknown to the police at local and neighbourhood levels, revealing that the dark figure of crime exists in various types of cities, with higher rates in suburban areas, low-housing neighborhoods, and areas with specific demographic characteristics.

BRITISH JOURNAL OF CRIMINOLOGY (2021)

添加到收藏夹

Proceedings Paper Computer Science, Theory & Methods

The effect of differential victim crime reporting on predictive policing systems

Nil-Jana Akpinar et al.

Summary: This study explores how differential victim crime reporting rates across geographical areas can affect the results of common crime hot spot prediction models. Such disparities may lead to the displacement of predicted hotspots, resulting in misallocations of policing resources.

PROCEEDINGS OF THE 2021 ACM CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY, FACCT 2021 (2021)

添加到收藏夹

Proceedings Paper Computer Science, Theory & Methods