The effects of transportation system improvements on urban performances with heterogeneous residents

Through developing a spatial equilibrium model for a linear monocentric city with a bimodal traffic corridor(i.e.,highway and public transit),this paper examines the effects of transportation improvements(including the decreases of the fixed travel cost,the travel time and monetary cost per unit distance)on urban spatial structure and the utilities of the two resident classes,namely car-available-residents(CARs)and car-unavailable-residents(CURs).As a result,it is demonstrated that the city size increases with the improvements of vehicle-highway system and the degree of CARs’travel mode choice rationality,but the improvement of public transit may produce a shrinkage rather than an expansion in city size.From the aspect of utility,both CARs and CURs benefit from the improvement of vehicle-highway system;however,the improvement of public transit might have an adverse effect on the utility of CARs.These findings would provide valuable reference for the future transportation and urban planning.

Refined analysis and a hierarchical multi-task learning approach for loan fraud detection

Fraud problems in loan application assessment cause significant losses for finance companies worldwide, and much research has focused on machine learning methods to improve the efficacy of fraud detection in some financial domains. However, diverse information falsification in individual fraud remains one of the most challenging problems in loan applications. To this end, we conducted an empirical study to explore the relationships between various fraud types and analyzed the factors influencing information fabrication. Weak relationships exist among different falsification types, and some essential factors play the same roles in different fraud types. In contrast, others have various or opposing effects on these types of frauds. Based on this finding, we propose a novel hierarchical multi-task learning approach to refine fraud-detection systems. Specifically, we first developed a hierarchical fraud category method to break down this problem into several subtasks according to the information types falsified by customers, reducing fraud identification's difficulty. Second, a heterogeneous network with a meta-path-based random walk and heterogeneous skip-gram model can solve the representation learning problem owing to the sophisticated relationships among the applicants' information. Furthermore, the final subtasks can be predicted using a multi-task learning approach with two prediction layers. The first layer provides the probabilities of general fraud categories as auxiliary information for the second layer, which is for specific subtask prediction. Finally, we conducted extensive experiments based on a real-world dataset to demonstrate the effectiveness of the proposed approach.

Sustainable urban transportation development in China:A behavioral perspective

The rapid development of economics requires highly efficient and environment-friendly urban transportation systems.Such requirement presents challenges in sustainable urban transportation.The analysis and understanding of transportation-related behaviors provide one approach to dealing with complicated transportation activities.In this study,the management of traffic systems is divided into four levels with a structural and systematic perspective.Then,several special cases from the perspective of behavior,including purchasing behaviors toward new energy vehicles,choice behaviors toward green travel,and behavioral reactions toward transportation demand management policies,are investigated.Several management suggestions are proposed for transportation authorities to improve sustainable traffic management.