No abstract

Traffic congestion has become a significant obstacle to the development of mega cities in China. Although local governments have used many resources in constructing road infrastructure, it is still insufficient for the increasing traffic demands. As a first step toward optimizing real-time traffic control, this study uses Shanghai Expressways as a case study to predict incident-related congestions. Our study proposes a graph convolutional network-based model to identify correlations in multi-dimensional sensor-detected data, while simultaneously taking into account environmental, spatiotemporal, and network features in predicting traffic conditions immediately after a traffic incident. The average accuracy, average AUC, and average F-1 score of the predictive model are 92.78%, 95.98%, and 88.78%, respectively, on small-scale ground-truth data. Furthermore, we improve the predictive model’s performance using semi-supervised learning by including more unlabeled data instances. As a result, the accuracy, AUC, and F-1 score of the model increase by 2.69%, 1.25%, and 4.72%, respectively. The findings of this article have important implications that can be used to improve the management and development of Expressways in Shanghai, as well as other metropolitan areas in China.

Purpose The purpose of this paper is to construct a multi-relational network for an online sharing platform in the age of the sharing economy, to identify the factors impacting users’ product adoption behavior and to predict consumers’ purchases of user-generated products on the platform. Design/methodology/approach The study conducted multi-relational network analyses of five different sub-networks in identifying influential factors for e-book adoption. Meanwhile, the study adopted machine learning methods with different classification algorithms and feature sets to predict users’ purchasing behaviors. Findings The authors found that an individual’s adoption of a product was correlated with his or her purchasing habits and collaboration with others on the online sharing platform. Through the inclusion of network features, the authors were able to build a predictive model that forecasted consumers’ purchases of user-generated e-books with reasonable accuracy. Research limitations/implications The interdisciplinary approach used in the study can serve as a good reference for identifying factors impacting the product adoption behavior of users in the online sharing platform, through employing different sociological and computational methods. Practical implications The outcome of the study has provided important managerial implications, especially for the design of social commerce platform in the age of the sharing economy. Social implications The authors verified the social influence impacting consumers’ product adoption behavior and shed light on the value of collaboration in the age of the sharing economy. Originality/value The study was the first to identify user-generated e-book adoption on an online sharing platform from a multi-relational network perspective. The idea and the approach supplied a new method of behavioral analysis in the context of a sharing economy.

No abstract

No abstract