Short-Term Segment-Level Crash Risk Prediction Using Advanced Data Modeling with Proactive and Reactive Crash Data

Highway crashes, along with the property damage, personal injuries, and fatalities that they cause, continue to present one of the most significant and critical transportation problems. At the same time, provision of safe travel is one of the main goals of any transportation system. For this reason, both in transportation research and practice much attention has been given to the analysis and modeling of traffic crashes, including the development of models that can be applied to predict crash occurrence and crash severity. In general, such models assess short-term crash risks at a given highway facility, thus providing intelligence that can be used to identify and implement traffic operations strategies for crash mitigation and prevention. This paper presents several crash risk and injury severity assessment models applied at a highway segment level, considering the input data that is typically collected or readily available to most transportation agencies in real-time and at a regional network scale, which would render them readily applicable in practice. The input data included roadway geometry characteristics, traffic flow characteristics, and weather condition data. The paper develops, tests, and compares the performance of models that employ Random effects Bayesian Logistics Regression, Gaussian Naïve Bayes, K-Nearest Neighbor, Random Forest, and Gradient Boosting Machine methods. The paper applies random oversampling examples (ROSE) method to deal with the problem of data imbalance associated with the injury severity analysis. The models were trained and tested using a dataset of 10,155 crashes that occurred on two interstate highways in New Jersey over a two-year period. The paper also analyzes the potential improvement in the prediction abilities of the tested models by adding reactive data to the analysis. To that end, traffic crashes were classified in multiple classes based on the driver age and the vehicle age to assess the impact of these attributes on driver injury severity outcomes. The results of this analysis are promising, showing that the simultaneous use of reactive and proactive data can improve the prediction performance of the presented models.

Real-Time Crash-Risk Optimization at Signalized Intersections

Over the past few decades, numerous adaptive traffic signal control (ATSC) algorithms have been proposed to alleviate traffic congestion and optimize traffic mobility using real-time traffic data, such as data from connected vehicles (CVs). However, most of the existing ATSC algorithms do not consider optimizing traffic safety, likely because of the lack of tools to evaluate safety in real time. In this paper, we propose a novel ATSC algorithm for real-time safety optimization. The algorithm utilizes a traditional Reinforcement Learning approach (i.e., Q-learning) as well as recently developed extreme value theory (EVT) real-time crash prediction models. The algorithm was validated using real-world traffic video data collected from two signalized intersections in British Columbia. The results indicated that, compared with an existing fully actuated signal controller, the developed algorithm can significantly reduce the real-time crash risk by 43% to 45% at the intersection’s approaches even at low CVs market penetration rates.

Aftershock: CEO Great Famine Experience and Stock Price Crash Risk

This study examines the effect of CEOs’ early-life traumatic experience on firm-specific stock price crash risk. Drawing on the idea of natural experiments, we take the Great Famine in China as an external traumatic event which cannot be selected or controlled by human. The analysis points out that compensation psychology and irrational defense psychology after the trauma of Great Famine are important factors that cause CEOs to hoard bad news. Based on a large sample of Chinese companies from 2007 to 2017, we find evidence that CEOs who experienced the Great Famine during early-life tend to hoard bad news, which result in higher stock price crash risk. The more severe and prolonged the Great Famine that the CEOs experienced, the greater the effect of this traumatic experience. CEOs decision-making power enhances the adverse effect of CEOs’ early-life traumatic experiences on crash risk. Findings of this study contributes to the literature by providing a new explanation for the stock price crash risk, which is of great significance for the sustained and healthy development of capital markets.

Older Driver Safety: A Renewed Perspective in a Survey Study in Illinois, U.S

Older adults (aged 65 or older) are at higher risk of involvement in motor vehicle crashes. Many studies have been conducted on older road users’ safety, but how older people’s driving behavior and demographic characteristics, and warnings of side effects of prescription medication, are associated with their crash risk has not been fully investigated. Aimed to address this knowledge gap, a mail survey of older drivers in Illinois, U.S. was conducted. Information on respondents’ driving behaviors, demographic characteristics, physical conditions, medication use, crash experience, etc. was gathered. Response distributions, odds ratios, and logistic regression models were employed to analyze the survey data. The results showed that most respondents kept a high level of mobility despite driving difficulty and medication use. Older drivers’ crash risk is mainly affected by external factors (driving exposure, alcohol consumption, and medication use) rather than their demographic characteristics and driving difficulty. Warnings from physicians on the side effects of prescription drugs had no significant effects on older drivers’ crash risk. Given the importance of mobility to older adults, the focus needs to be placed on providing a safe roadway system and safe driving advice for older drivers, particularly those who are on medication.

Investor Sentiment and Stock Price Crash Risk in the Chinese Stock Market

This paper uses the partial least squares method to construct the investor sentiment index in Chinese stock market. The Shanghai Stock Exchange 180 Index and the Shenzhen Stock Exchange 100 Index are used as samples. From the perspectives of holistic sentiment and heterogeneous sentiment, this paper studies the impact of investor sentiment on stock price crash risk. The results show that investor sentiment can significantly affect stock price crash risk in Shanghai and Shenzhen A-share markets, especially in the Shenzhen A-share market no matter from which perspective. And investor pessimism has a greater impact on stock price crash risk in the Shenzhen A-share market from the perspective of heterogeneous sentiment. Compared with the available researches, this paper makes two contributions: (i) the comparative analysis is adopted to discuss the differences between Shanghai and Shenzhen A-share markets, abandoning the research approach that takes the two markets as a whole in existing literature, and (ii) this paper not only studies the impact of investor holistic sentiment on stock price crash risk from a macro perspective, but also adds a more micro heterogeneous sentiment and conducts a comparative analysis.