Automated Enforcement and Traffic Safety

74 Pages Posted: 27 Feb 2023

See all articles by Aaron Cheng

Aaron Cheng

London School of Economics - Department of Management

Zhanyu Dong

Sun Yat-sen University (SYSU) - School of Business; The University of Hong Kong - Faculty of Business and Economics

Min-Seok Pang

University of Wisconsin - Madison - Department of Operations and Information Management

Date Written: June 05, 2024

Abstract

Traffic safety remains a critical challenge for society and public policy. Conventional law enforcement by human police is often cost-ineffective due to information asymmetry and negative externalities of unsafe driving behaviors. Although automated enforcement, in the form of traffic cameras, has been increasingly implemented in recent decades, its impact on road safety and the underlying mechanisms are still debated in the literature. Using a longitudinal dataset of traffic camera installations and police reports of road accidents in a metropolitan city in China, we investigate accident trends near road intersections with and without traffic cameras. We differentiate between advanced cameras, which constantly record video and use machine learning techniques to detect various traffic violations, and conventional cameras, which identify limited violations through temporary image capture triggered by nearby electromagnetic devices. Using an event study design that exploits the staggered installation of traffic cameras, we observe a significant and persistent reduction in total accidents near advanced cameras, compared to locations without cameras or with only conventional cameras. Our analysis reveals three underlying mechanisms: (i) advanced cameras exhibit enhanced technical capabilities in automating violation detection (automated detection effect); (ii) advanced cameras constantly monitor and record road conditions, augmenting accident cause identification (real-time recording effect); and (iii) both capabilities collectively establish technology-enabled deterrence, leading to driver awareness of these cameras and behavioral adjustments that mitigate accident risks (driver learning effect). This work contributes to the fields of information systems, transportation economics, and criminology, providing policy insights into the effective implementation of automated enforcement to improve traffic safety.

Keywords: Automated Enforcement, Traffic Safety, Deterrence, Event Study

JEL Classification: M15, R41, O18, I18

Suggested Citation

Cheng, Zhi (Aaron) and Dong, Zhanyu and Pang, Min-Seok,
Automated Enforcement and Traffic Safety
(June 05, 2024). Available at SSRN: https://ssrn.com/abstract=4366385 or http://dx.doi.org/10.2139/ssrn.4366385

Zhi (Aaron) Cheng (Contact Author)

London School of Economics - Department of Management ( email )

Houghton Street
London, WC2A 2AE
United Kingdom

Zhanyu Dong

Sun Yat-sen University (SYSU) - School of Business ( email )

No. 66, Gongchang Rd., Guangming Dist.
Shenzhen, Guangdong 518107
China

The University of Hong Kong - Faculty of Business and Economics ( email )

Pokfulam Road
Hong Kong
China

Min-Seok Pang

University of Wisconsin - Madison - Department of Operations and Information Management ( email )

Madison, WI
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
158
Abstract Views
1,276
Rank
372,277
PlumX Metrics