Modeling and Prediction of Ride-Sharing Utilization Dynamics

Abstract

The potential of an efficient ride-sharing scheme to significantly reduce traffic congestion, lower emission level, and drivers’ stress, as well as facilitating the introduction of smart cities has been widely demonstrated in recent years. Furthermore, ride sharing can be implemented within a sound economic regime through the involvement of commercial services that creates a win-win for all parties (e.g., Uber, Lyft or Sidecar). This positive thrust however is faced with several delaying factors, one of which is the volatility and unpredictability of the potential benefit (or utilization) of ride-sharing at different times, and in different places. Better understanding of ride-sharing dynamics can help policy makers and urban planners in increase the city’s “ride-sharing friendliness” either by designing new ride-sharing oriented systems, as well as by providing ride-sharing service operators better tools to optimize their services. In this work the following research questions are posed: (a) Is ride-sharing utilization stable over time or does it undergo significant changes? (b) If ride-sharing utilization is dynamic can it be correlated with some traceable features of the traffic? and (c) If ride-sharing utilization is dynamic can it be predicted ahead of time? We analyze a dataset of over 14 million taxi trips taken in New York City. We propose a dynamic travel network approach for modeling and forecasting the potential ride-sharing utilization over time, showing it to be highly volatile. In order to model the utilization's dynamics, we propose a network-centric approach, projecting the aggregated traffic taken from continuous time periods into a feature space comprised of topological features of the network implied by this traffic. This feature space is then used to model the dynamics of ride-sharing utilization over time. The results of our analysis demonstrate the significant volatility of ride-sharing utilization over time, indicating that any policy, design, or plan that would disregard this aspect and chose a static paradigm would undoubtably be either highly inefficient or provide insufficient resources. We show that using our suggested approach it is possible to model the potential utilization of ride sharing based on the topological properties of the rides network. We also show that using this method the potential utilization can be forecasting a few hours ahead of time. One anecdotal derivation of the latter is that perfectly guessing the destination of a New York taxi rider becomes nearly three times easier than rolling a “Snake Eyes” at a casino.

DNN Intellectual Property Extraction Using Composite Data

“…A swarm contains a group of autonomous robots without central coordination, which is designed to maximize the performance of a specific task [51]. Tasks that have been of particular interest to researchers in recent years include synergetic mission planning [52], patrolling [53], fault tolerance cooperation [54], network security [55], crowds modeling [56], swarm control [57], human design of mission plans [58], role assignment [59], multi-robot path planning [60], traffic control [61], formation generation [62], formation keeping [63], exploration and mapping [64], modeling of financial systems [65], target tracking [66,67], collaborative cleaning [68], control architecture for drones swarm [69], and target search [70].…”

Meta-Learning over Time for Destination Prediction Tasks

“…The task of destination and/or trajectory prediction is well-known in the domains of urban planning and management, intelligent transportation systems, "smart cities, " and ride-sharing applications, leading to a proliferation of research in the past few years [2,3,60,61,66,67]. Recent events have also energized a sub-field of mobility modeling and destination prediction for the purposes of pandemic analysis [23].…”

Evaluation Methods for the Impacts of Shared Mobility: Classification and Critical Review

“…In recent years, several academic papers have reported on efforts to use disaggregate (micro) models to describe the functioning of one-way car sharing [122,123], bike sharing [124], and TNCs [69,125,126]. In the meantime, a switch to the topic of vehicle automation has led to a shift in the models employed, even though many of the models can still be used to assess dynamic ridesharing [73,[127][128][129]. These models can describe the supply of demand-responsive systems in a realistic way because they model each vehicle specifically and use matching to one particular client.…”