2021
DOI: 10.1109/tkde.2019.2955686
|View full text |Cite
|
Sign up to set email alerts
|

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

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 23 publications
(6 citation statements)
references
References 35 publications
0
4
0
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
“…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%
“…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%
“…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%
“…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%