Predicting real-time surge pricing of ride-sourcing companies

Battifarano, Matthew; Qian, Sean

doi:10.1016/j.trc.2019.08.019

Cited by 51 publications

(24 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dynamic pricing serves as an incentive for Uber drivers to drive to areas of the city, where demand for rides is higher, and thereby helps the operator with real-time adjustment and proactive positioning of the ride-hailing fleet to changing demand patterns. However, little is known about the proprietary surge pricing process applied by companies (Battifarano and Qian 2019). These benefits should be contextualized within research literature that has pointed to significant limitations of the "gig economy" model.…”

Section: The Ride-hailing Short-term Demand Forecasting Problemmentioning

confidence: 99%

Short-Term Prediction of Demand for Ride-Hailing Services: A Deep Learning Approach

Chen¹,

Thakuriah

Ampountolas

2021

J. Big Data Anal. Transp.

View full text Add to dashboard Cite

As ride-hailing services become increasingly popular, being able to accurately predict demand for such services can help operators efficiently allocate drivers to customers, and reduce idle time, improve traffic congestion, and enhance the passenger experience. This paper proposes UberNet, a deep learning convolutional neural network for short-time prediction of demand for ride-hailing services. Exploiting traditional time series approaches for this problem is challenging due to strong surges and declines in pickups, as well as spatial concentrations of demand. This leads to pickup patterns that are unevenly distributed over time and space. UberNet employs a multivariate framework that utilises a number of temporal and spatial features that have been found in the literature to explain demand for ride-hailing services. Specifically, the proposed model includes two sub-networks that aim to encode the source series of various features and decode the predicting series, respectively. To assess the performance and effectiveness of UberNet, we use 9 months of Uber pickup data in 2014 and 28 spatial and temporal features from New York City. We use a number of features suggested by the transport operations and travel behaviour research areas as being relevant to passenger demand prediction, e.g., weather, temporal factors, socioeconomic and demographics characteristics, as well as travel-to-work, built environment and social factors such as crime level, within a multivariate framework, that leads to operational and policy insights for multiple communities: the ride-hailing operator, passengers, third-part location-based service providers and revenue opportunities to drivers, and transport operators such as road traffic authorities, and public transport agencies. By comparing the performance of UberNet with several other approaches, we show that the prediction quality of the model is highly competitive. Further, Ubernet’s prediction performance is better when using economic, social and built environment features. This suggests that Ubernet is more naturally suited to including complex motivators of travel behavior in making real-time demand predictions for ride-hailing services.

show abstract

Section: The Ride-hailing Short-term Demand Forecasting Problemmentioning

confidence: 99%

Short-Term Prediction of Demand for Ride-Hailing Services: A Deep Learning Approach

Chen¹,

Thakuriah

Ampountolas

2021

J. Big Data Anal. Transp.

View full text Add to dashboard Cite

show abstract

“…The intermediary faces the problem of spatial-temporal supply-demand imbalance as well. To balance the supply-demand status among areas, the intermediary can first predict market demand [6,161,164], then adopt spatial discriminatory pricing accordingly (i.e., set a higher price in high-demand areas to stimulate vacant drivers to move to highdemand zones for more profits). In this way, even when demand is still not fulfilled, the intermediary still profits more from charging a higher price in less-supplied areas [6,156].…”

Section: Intermediary Pricingmentioning

confidence: 99%

“…Despite the fruitfulness of the theoretical research, empirical research is rarely conducted, including research on the profitability difference between dynamic pricing (e.g., ride hailing platforms) and static pricing (e.g., the traditional taxi industry). Battifarano and Qian [161] empirically validated that the surge multiplier is affected by weather conditions, traffic conditions, and public events, while regional factors (e.g., the departure and destination locations and trip distance), time factors (e.g., peak hours), and macrofactors (e.g., local income level, local taxi price) were not examined. Additionally, Farajallah, Hammond [126] examined factors that affect a driver's pricing decision in BlaBlaCar by adopting a hedonic-pricing-like model, which inspires the idea that hedonic-pricing-like models can also be employed to empirically investigate pricing strategies of different market segmentations (e.g., express service and select service provided by Didi).…”

Section: Intermediary Pricingmentioning

confidence: 99%

A Systematic Literature Review on Pricing Strategies in the Sharing Economy

Yang

Xia

2021

Sustainability

View full text Add to dashboard Cite

As an emerging business model, the sharing economy has gained a large amount of academic attention; the pricing problem in the sharing economy has also been widely investigated. Aiming to capture the current state-of-the-art research on pricing strategies in the sharing economy and foreseeing directions for future research, this article conducts a systematic literature review and content analysis of 158 articles from the Scopus and Web of Science databases. As a result, first, this review proposes an extended definition covering B2C and C2C models and a model structure covering the entire supply chain, based on which 158 articles are categorized into nine sub-models covering 30 scenarios. Second, the general characteristics (i.e., research fields, time and journal distributions, research themes and scenarios) and technical details (i.e., theories, methodologies, approaches, models, and conclusions) of the 158 articles are reviewed and summarized by the pricing party, business mode, and scenario. Finally, this review proposes some future research directions of existing scenarios from the perspectives of information asymmetry, market competition, and empirical approaches, and discusses some extensions, including uninvestigated scenarios and COVID-19-related topics; correspondingly, this review suggests some analytical models and empirical approaches that can be employed to fill these gaps. The proposed research directions and corresponding approaches can be references for future research.

show abstract

“…More recently, Battifarano and Qian (2019) explored the spatio-temporal correlations between the urban environment, traffic flow characteristics, and surge multipliers and proposed a general framework for predicting the shortterm evolution of surge multipliers in real-time using a log-linear model with 1 regularization, integrated with pattern clustering. The modeling algorithm is validated by using Uber and Lyft data from Pittsburgh (22).…”

Section: Literature On Transportation Analysis Utilizing Regularizatimentioning

confidence: 99%

Linear Regularization-based Analysis and Prediction of Human Mobility in the U.S. during the COVID-19 Pandemic

Chakraborty¹,

Mahmud²,

Gates³

et al. 2020

Preprint

View full text Add to dashboard Cite

Since the increasing spread of COVID-19 in the U.S., with currently the highest number of confirmed cases and deaths in the world, most states in the nation have enforced travel restrictions resulting in drastic reductions in mobility and travel. However, the overall impact and long-term implications of this crisis to mobility still remain uncertain. To this end, this study develops an analytical framework that determines the most significant factors impacting human mobility and travel in the U.S. during the pandemic. In particular, we use Least Absolute Shrinkage and Selection Operator (LASSO) to identify the significant variables influencing human mobility and utilize linear regularization algorithms, including Ridge, LASSO, and Elastic Net modeling techniques to model and predict human mobility and travel. State-level data were obtained from various open-access sources for the period from January 1, 2020 to June 13, 2020. The entire data set was divided into a training data-set and a test data-set and the variables selected by LASSO were used to train four different models by ordinary linear regression, Ridge regression, LASSO and Elastic Net regression algorithms, using the training data-set. Finally, the prediction accuracy of the developed models was examined on the test data. The results indicate that among all models, the Ridge regression provides the most superior performance with the least error, while both LASSO and Elastic Net performed better than the ordinary linear model.

show abstract

Predicting real-time surge pricing of ride-sourcing companies

Cited by 51 publications

References 25 publications

Short-Term Prediction of Demand for Ride-Hailing Services: A Deep Learning Approach

Short-Term Prediction of Demand for Ride-Hailing Services: A Deep Learning Approach

A Systematic Literature Review on Pricing Strategies in the Sharing Economy

Linear Regularization-based Analysis and Prediction of Human Mobility in the U.S. during the COVID-19 Pandemic

Contact Info

Product

Resources

About