skip to main content

Title: Fairness-Aware Demand Prediction for New Mobility
Emerging transportation modes, including car-sharing, bike-sharing, and ride-hailing, are transforming urban mobility yet have been shown to reinforce socioeconomic inequity. These services rely on accurate demand prediction, but the demand data on which these models are trained reflect biases around demographics, socioeconomic conditions, and entrenched geographic patterns. To address these biases and improve fairness, we present FairST, a fairness-aware demand prediction model for spatiotemporal urban applications, with emphasis on new mobility. We use 1D (time-varying, space-constant), 2D (space-varying, time-constant) and 3D (both time- and space-varying) convolutional branches to integrate heterogeneous features, while including fairness metrics as a form of regularization to improve equity across demographic groups. We propose two spatiotemporal fairness metrics, region-based fairness gap (RFG), applicable when demographic information is provided as a constant for a region, and individual-based fairness gap (IFG), applicable when a continuous distribution of demographic information is available. Experimental results on bike share and ride share datasets show that FairST can reduce inequity in demand prediction for multiple sensitive attributes (i.e. race, age, and education level), while achieving better accuracy than even state-of-the-art fairness-oblivious methods.
Authors:
;
Award ID(s):
1934405 1740996
Publication Date:
NSF-PAR ID:
10188200
Journal Name:
Proceedings of the AAAI Conference on Artificial Intelligence
Volume:
34
Issue:
01
Page Range or eLocation-ID:
1079 to 1087
ISSN:
2159-5399
Sponsoring Org:
National Science Foundation
More Like this
  1. While ride-sharing has emerged as a popular form of transportation in urban areas due to its on-demand convenience, it has become a major contributor to carbon emissions, with recent studies suggesting it is 47% more carbon-intensive than personal car trips. In this paper, we examine the feasibility, costs, and carbon benefits of using electric bike-sharing---a low carbon form of ride-sharing---as a potential substitute for shorter ride-sharing trips, with the overall goal of greening the ride-sharing ecosystem. Using public datasets from New York City, our analysis shows that nearly half of the taxi and rideshare trips in New York are shortsmore »trips of less than 3.5km, and that biking is actually faster than using a car for ultra-short trips of 2km or less. We analyze the cost and carbon benefits of different levels of ride substitution under various scenarios. We find that the additional bikes required to satisfy increased demand from ride substitution increases sub-linearly and results in 6.6% carbon emission reduction for 10% taxi ride substitution. Moreover, this reduction can be achieved through a hybrid mix that requires only a quarter of the bikes to be electric bikes, which reduces system costs. We also find that expanding bike-share systems to new areas that lack bike-share coverage requires additional investments due to the need for new bike stations and bike capacity to satisfy demand but also provides substantial carbon emission reductions. Finally, frequent station repositioning can reduce the number of bikes needed in the system by up to a third for a minimal increase in carbon emissions of 2% from the trucks required to perform repositioning, providing an interesting tradeoff between capital costs and carbon emissions.« less
  2. While ride-sharing has emerged as a popular form of transportation in urban areas due to its on-demand convenience, it has become a major contributor to carbon emissions, with recent studies suggesting it is 47% more carbon-intensive than personal car trips. In this paper, we examine the feasibility, costs, and carbon benefits of using electric bike-sharing—a low carbon form of ride-sharing—as a potential substitute for shorter ride-sharing trips, with the overall goal of greening the ride-sharing ecosystem. Using public datasets from New York City, our analysis shows that nearly half of the taxi and rideshare trips in New York are shortsmore »trips of less than 3.5km, and that biking is actually faster than using a car for ultra-short trips of 2km or less. We analyze the cost and carbon benefits of different levels of ride substitution under various scenarios. We find that the additional bikes required to satisfy increased demand from ride substitution increases sub-linearly and results in 6.6% carbon emission reduction for 10% taxi ride substitution. Moreover, this reduction can be achieved through a hybrid mix that requires only a quarter of the bikes to be electric bikes, which reduces system costs. We also find that expanding bike-share systems to new areas that lack bike-share coverage requires additional investments due to the need for new bike stations and bike capacity to satisfy demand but also provides substantial carbon emission reductions. Finally, frequent station repositioning can reduce the number of bikes needed in the system by up to a third for a minimal increase in carbon emissions of 2% from the trucks required to perform repositioning, providing an interesting tradeoff between capital costs and carbon emissions.« less
  3. Background Cardiovascular disease (CVD) disparities are a particularly devastating manifestation of health inequity. Despite advancements in prevention and treatment, CVD is still the leading cause of death in the United States. Additionally, research indicates that African American (AA) and other ethnic-minority populations are affected by CVD at earlier ages than white Americans. Given that AAs are the fastest-growing population of smartphone owners and users, mobile health (mHealth) technologies offer the unparalleled potential to prevent or improve self-management of chronic disease among this population. Objective To address the unmet need for culturally tailored primordial prevention CVD–focused mHealth interventions, the MOYO appmore »was cocreated with the involvement of young people from this priority community. The overall project aims to develop and evaluate the effectiveness of a novel smartphone app designed to reduce CVD risk factors among urban-AAs, 18-29 years of age. Methods The theoretical underpinning will combine the principles of community-based participatory research and the agile software development framework. The primary outcome goals of the study will be to determine the usability, acceptability, and functionality of the MOYO app, and to build a cloud-based data collection infrastructure suitable for digital epidemiology in a disparity population. Changes in health-related parameters over a 24-week period as determined by both passive (eg, physical activity levels, sleep duration, social networking) and active (eg, use of mood measures, surveys, uploading pictures of meals and blood pressure readings) measures will be the secondary outcome. Participants will be recruited from a majority AA “large city” school district, 2 historically black colleges or universities, and 1 urban undergraduate college. Following baseline screening for inclusion (administered in person), participants will receive the beta version of the MOYO app. Participants will be monitored during a 24-week pilot period. Analyses of varying data including social network dynamics, standard metrics of activity, percentage of time away from a given radius of home, circadian rhythm metrics, and proxies for sleep will be performed. Together with external variables (eg, weather, pollution, and socioeconomic indicators such as food access), these metrics will be used to train machine-learning frameworks to regress them on the self-reported quality of life indicators. Results This 5-year study (2015-2020) is currently in the implementation phase. We believe that MOYO can build upon findings of classical epidemiology and longitudinal studies like the Jackson Heart Study by adding greater granularity to our knowledge of the exposures and behaviors that affect health and disease, and creating a channel for outreach capable of launching interventions, clinical trials, and enhancements of health literacy. Conclusions The results of this pilot will provide valuable information about community cocreation of mHealth programs, efficacious design features, and essential infrastructure for digital epidemiology among young AA adults. International Registered Report Identifier (IRRID) DERR1-10.2196/16699« less
  4. Urban dispersal events occur when an unexpectedly large number of people leave an area in a relatively short period of time. It is beneficial for the city authorities, such as law enforcement and city management, to have an advance knowledge of such events, as it can help them mitigate the safety risks and handle important challenges such as managing traffic, and so forth. Predicting dispersal events is also beneficial to Taxi drivers and/or ride-sharing services, as it will help them respond to an unexpected demand and gain competitive advantage. Large urban datasets such as detailed trip records and point ofmore »interest ( POI ) data make such predictions achievable. The related literature mainly focused on taxi demand prediction. The pattern of the demand was assumed to be repetitive and proposed methods aimed at capturing those patterns. However, dispersal events are, by definition, violations of those patterns and are, understandably, missed by the methods in the literature. We proposed a different approach in our prior work [32]. We showed that dispersal events can be predicted by learning the complex patterns of arrival and other features that precede them in time. We proposed a survival analysis formulation of this problem and proposed a two-stage framework (DILSA), where a deep learning model predicted the survival function at each point in time in the future. We used that prediction to determine the time of the dispersal event in the future, or its non-occurrence. However, DILSA is subject to a few limitations. First, based on evidence from the data, mobility patterns can vary through time at a given location. DILSA does not distinguish between different mobility patterns through time. Second, mobility patterns are also different for different locations. DILSA does not have the capability to directly distinguish between different locations based on their mobility patterns. In this article, we address these limitations by proposing a method to capture the interaction between POIs and mobility patterns and we create vector representations of locations based on their mobility patterns. We call our new method DILSA+. We conduct extensive case studies and experiments on the NYC Yellow taxi dataset from 2014 to 2016. Results show that DILSA+ can predict events in the next 5 hours with an F1-score of 0.66. It is significantly better than DILSA and the state-of-the-art deep learning approaches for taxi demand prediction.« less
  5. As more people move back into densely populated cities, bike sharing is emerging as an important mode of urban mobility. In a typical bike-sharing system (BSS), riders arrive at a station and take a bike if it is available. After retrieving a bike, they ride it for a while, then return it to a station near their final destinations. Since space is limited in cities, each station has a finite capacity of docks, which cannot hold more bikes than its capacity. In this paper, we study BSSs with stations having a finite capacity. By an appropriate scaling of our stochasticmore »model, we prove a mean-field limit and a central limit theorem for an empirical process of the number of stations with k bikes. The mean-field limit and the central limit theorem provide insight on the mean, variance, and sample path dynamics of large-scale BSSs. We also leverage our results to estimate confidence intervals for various performance measures such as the proportion of empty stations, the proportion of full stations, and the number of bikes in circulation. These performance measures have the potential to inform the operations and design of future BSSs.« less