Predicting Taxi and Uber Demand in Cities: Approaching the Limit of Predictability

Zhao, Kai; Khryashchev, Denis; Vo, Huy T.

doi:10.1109/tkde.2019.2955686

Cited by 23 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the real-time requests or online settings, some dynamic models are proposed to optimize the car dispatch problem with heuristic idea [12,13]. With the development of the neural networks, many works [14,15] are trying to predict the demand in real time, which can help the dispatch tasks get prepared in advance. ere are some works to investigate the trajectories similarity, which can help saving the vehicles number [16].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Optimization Algorithm Design for the Taxi-Sharing Problem and Application

Wang

2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

With the development of mobility techniques, the transportation systems become smarter, pursuing higher goals, such as convenience for passengers and low cost. In this work, we investigate the taxi-sharing system, which is a promising system recently. The passengers can share the same taxis to different destinations to save cost. Considering the property of taxis’ routes, the corresponding model is established and our aim is to design the trip for each taxi to reduce the total number of taxi trips in the whole system if one taxi can be shared by several passengers. Compared with the previous work, we do not have any constraint about the taxi stations. The taxi trips have more flexibility in reality. We analyze this problem and prove it is NP-Complete. There are two proposed algorithms to solve this problem, one is a heuristic algorithm and the other is an approximate algorithm. In the experiment, two real-world taxi data sets are tested, and our algorithm shows the superiority of our taxi-sharing system. Using the taxi-sharing system, the number of trips can be reduced by about 30 % .

show abstract

Section: Related Workmentioning

confidence: 99%

“…Continue; (13) if f[j] �� ∅ then (14) f[j] � p j (15) res � res + 1 (16) return res ALGORITHM 1: Greedy algorithm…”

Section: Theorem 4 Is Approximation Algorithm Can Achieve O(log M) Approximationmentioning

confidence: 99%

Optimization Algorithm Design for the Taxi-Sharing Problem and Application

Wang

2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…The ODM literature predominantly focuses on predicting the number of short-term customer requests (5 -60 minutes) using time-series or machine learning approaches (Moreira-Matias et al, 2013;Jiang et al, 2019). Typically, most models are developed using GPS trace data as predictors (Davis et al 2018;Zhao et al, 2019;Luo et al, 2020), while few studies combined data from multiple sources to increase prediction accuracy (Rodrigues et al, 2019). Besides, a common strategy is to adopt more than one error measure (Equations 2 -5) to evaluate the prediction models (e.g., Ke et al, 2017;Jiang et al, 2019;Li and Wan, 2019).…”

Section: Quantitative Approachesmentioning

confidence: 99%

Air taxi service for urban mobility: A critical review of recent developments, future challenges, and opportunities

Rajendran

Srinivas

2020

Transportation Research Part E: Logistics and Transportation Re

127

View full text Add to dashboard Cite

Expected to operate in the imminent future, air taxi service (ATS) is an aerial on-demand transport for a single passenger or a small group of riders, which seeks to transform the method of everyday commute. This uncharted territory in the emerging transportation world is anticipated to enable consumers bypass traffic congestion in urban road networks. By adopting an electric vertical takeoff and landing concept (eVTOL), air taxis could be operational from skyports retrofitted on building rooftops, thus gaining advantage from an implementation standpoint. Motivated by the potential impact of ATS, this study provides a review of air taxi systems and associated operations. We first discuss the current developments in the ATS (demand prediction, air taxi network design, and vehicle configuration). Next, we anticipate potential future challenges of ATS from an operations management perspective, and review the existing literature that could be leveraged to tackle these problems (ride-matching, pricing strategies, vehicle maintenance scheduling, and pilot training and recruitment). Finally, we detail future research opportunities in the air taxi domain.

show abstract

“…However, the problem of finding all the subsets of a given set has exponential computational complexity. In practice, we use the estimator proposed by Lempel and Ziv [29] that rapidly converges to the value of the entropy. For the T -length spectrum observation sequence y f , the Lempel-Ziv entropy estimator is defined as…”

Section: Predictability Analysismentioning

confidence: 99%

Recovering Missing Values From Corrupted Historical Observations: Approaching the Limit of Predictability in Spectrum Prediction Tasks

Chen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Spectrum prediction is a key enabler of a range of emerging applications, from adaptive spectrum sensing to agile and proactive decision making, for dynamic spectrum access. Due to the fact that spectrum sensors easily experience an issue of missing readings and anomaly pollution, spectrum prediction with incomplete and corrupted historical observations has caused extensive concern. In this paper, we aim to tackle the challenging problem on how to accurately and efficiently recover the missing values from corrupted historical spectrum observations for approaching the limit of predictability in the spectrum prediction tasks. Specially, we first formulate a hankelized time-structured spectrum tensor that can naturally preserve both spectral and temporal dependencies among the historical spectrum observations. We then model the spectrum data recovery problem as tensor completion with its latent low-rank structure and sparse anomaly property. To efficiently solve the optimization problem, we design a robust online spectrum data recovery algorithm based on the alternating direction method. In addition, we also introduce the concept of maximum predictability to reveal the harmful effects of missing data and anomalies, as well as to evaluate the effectiveness of our proposed algorithm from an information theory perspective. Extensive experimental evaluations on the real-world spectrum observation dataset show that the proposed algorithm achieves significantly better spectrum data recovery performance in terms of both recovery accuracy and computation efficiency. It also indicates that not only the predictability of the frequency bands but also the prediction accuracy of any predictive algorithm can be improved by the proposed algorithm.

show abstract

Predicting Taxi and Uber Demand in Cities: Approaching the Limit of Predictability

Cited by 23 publications

References 35 publications

Optimization Algorithm Design for the Taxi-Sharing Problem and Application

Optimization Algorithm Design for the Taxi-Sharing Problem and Application

Air taxi service for urban mobility: A critical review of recent developments, future challenges, and opportunities

Recovering Missing Values From Corrupted Historical Observations: Approaching the Limit of Predictability in Spectrum Prediction Tasks

Contact Info

Product

Resources

About