Ridesourcing platforms like Uber and Didi are getting more and more popular around the world. However, unauthorized ridesourcing activities taking advantages of the sharing economy can greatly impair the healthy development of this emerging industry. As the first step to regulate on-demand ride services and eliminate black market, we design a method to detect ridesourcing cars from a pool of cars based on their trajectories. Since licensed ridesourcing car traces are not openly available and may be completely missing in some cities due to legal issues, we turn to transferring knowledge from public transport open data, i.e, taxis and buses, to ridesourcing detection among ordinary vehicles. We propose a two-stage transfer learning framework. In Stage 1, we take taxi and bus data as input to learn a random forest (RF) classifier using trajectory features shared by taxis/buses and ridesourcing/other cars. Then, we use the RF to label all the candidate cars. In Stage 2, leveraging the subset of high confident labels from the previous stage as input, we further learn a convolutional neural network (CNN) classifier for ridesourcing detection, and iteratively refine RF and CNN, as well as the feature set, via a co-training process. Finally, we use the resulting ensemble of RF and CNN to identify the ridesourcing cars in the candidate pool. Experiments on real car, taxi and bus traces show that our transfer learning framework, with no need of a pre-labeled ridesourcing dataset, can achieve similar accuracy as the supervised learning methods.
Ride-sourcing services are becoming an increasingly popular transportation mode in cities all over the world. With real-time information from both drivers and passengers, the ride-sourcing platform can reduce matching frictions and improve efficiencies by surge pricing, optimal vehicle-trip assignment, and proactive ridesplitting strategies. An important foundation of these strategies is the short-term supply-demand forecasting. In this paper, we tackle the problem of predicting the short-term supply-demand gap of ride-sourcing services. In contrast to the previous studies that partitioned a city area into numerous square lattices, we partition the city area into various regular hexagon lattices, which is motivated by the fact that hexagonal segmentation has an unambiguous neighborhood definition, smaller edge-to-area ratio, and isotropy.
Uber and Lyft have touted their ride-hailing companies as'car-cutters' by reducing the number of vehicle ownership in US metro areas, but a new study finds the claims are far from the truth. A team from Carnegie Mellon University uncovered, on average, a 0.7 percent increase in personal vehicles after the two firms unleashed drivers into a new market starting in 2010 through 2017. Larger increases of vehicle registrations were observed in cities that were car-dependent, had slower rates of population growth, included households with more children or were deemed lower income. Although the uptick is small, researchers told Wired that the new study is an improvement on previous work that analyzed just the state-level and found Uber and Lyft reduce car ownership rates. Uber and Lyft have touted their ride-hailing companies as'car-cutters' by reducing the number of vehicle ownership in US metro areas, but a new study finds the claims are far from the truth Jeremy Michalek, a professor of engineering and public policy at Carnegie Mellon University and co-author on the study, said: 'I would have expected people to own fewer vehicles once they gain access to this alternative transportation mode.' 'But that's not what we see in the data.
In order to collectively forecast the demand of ride-sourcing services in all regions of a city, convolutional neural networks (CNNs) have been applied with commendable results. However, local statistical differences throughout the geographical layout of the city make the spatial stationarity assumption of the convolution invalid, which limits the performance of CNNs on demand forecasting task. Hence, we propose a novel deep learning framework called LC-ST- FCN (locally-connected spatiotemporal fully-convolutional neural network) that consists of a stack of 3D convolutional layers, 2D (standard) convolutional layers, and locally connected convolutional layers. This fully convolutional architecture maintains the spatial coordinates of the input and no spatial information is lost between layers. Features are fused across layers to define a tunable nonlinear local-to-global-to-local representation, where both global and local statistics can be learned to improve predictive performance. Furthermore, as the local statistics vary from region to region, the arithmetic-mean-based metrics frequently used in spatial stationarity situations cannot effectively evaluate the models. We propose a weighted-arithmetic approach to deal with this situation. Our findings are threefold: (1) 3D convolutions are more suitable for spatiotemporal feature learning compared to 2D convolutions; And the locally connected convolutional layers can deal with the impact of local statistical differences well, better than fully connected layers or standard convolutional layers.
Joe Castiglione compares his job to playing SimCity. As the deputy director for technology, data, and analysis at the San Francisco County Transportation Authority, Castiglione spends his days manipulating models of the Bay Area and its 7 million residents. From wide-sweeping ridership and traffic data to deep dives into personal travel choices via surveys, his models are able to estimate the number of people who will disembark at a specific train platform at a certain time of day and predict how that might change if a new housing development is built nearby, or if train-frequency is increased. The models are exceedingly complex, because people are so complex. "Think about the travel choices you've made in the last week, or the last year," Castiglione says. "How do you time your trips? What tradeoffs do you make? What modes of transportation do you use? How do those choices change from day to day?"