Dynamic taxi pricing

Cheng Zeng, Nir Oren

Research output: Contribution to conferencePaper

4 Citations (Scopus)
55 Downloads (Pure)

Abstract

Taxi journeys are usually priced according to the distance covered and time taken for the trip. Such a fixed cost strategy is simple to understand, but does not take into account the likelihood that a taxi can pick up additional pas- sengers at the original passenger’s destination. In this paper we investigate dynamic taxi pricing strategies. By using do- main knowledge, such strategies discount trips to locations containing many potential passengers, and increase fares to those areas with few potential passengers. Identifying a closed form optimal dynamic pricing strategy is difficult, and by rep- resenting the domain as an MDP, we can identify an optimal strategy for specific domains. We empirically compare such dynamic pricing strategies with fixed cost strategies, and sug- gest future extensions to this work.
Original languageEnglish
Pages1135-1136
Number of pages2
DOIs
Publication statusPublished - Aug 2014
EventEuropean Conference on Artificial Intelligence (ECAI-2014) - Prague, United Kingdom
Duration: 18 Aug 201422 Aug 2014

Conference

ConferenceEuropean Conference on Artificial Intelligence (ECAI-2014)
CountryUnited Kingdom
CityPrague
Period18/08/1422/08/14

Fingerprint

Costs

Cite this

Zeng, C., & Oren, N. (2014). Dynamic taxi pricing. 1135-1136. Paper presented at European Conference on Artificial Intelligence (ECAI-2014), Prague, United Kingdom. https://doi.org/10.3233/978-1-61499-419-0-1135

Dynamic taxi pricing. / Zeng, Cheng; Oren, Nir.

2014. 1135-1136 Paper presented at European Conference on Artificial Intelligence (ECAI-2014), Prague, United Kingdom.

Research output: Contribution to conferencePaper

Zeng, C & Oren, N 2014, 'Dynamic taxi pricing' Paper presented at European Conference on Artificial Intelligence (ECAI-2014), Prague, United Kingdom, 18/08/14 - 22/08/14, pp. 1135-1136. https://doi.org/10.3233/978-1-61499-419-0-1135
Zeng C, Oren N. Dynamic taxi pricing. 2014. Paper presented at European Conference on Artificial Intelligence (ECAI-2014), Prague, United Kingdom. https://doi.org/10.3233/978-1-61499-419-0-1135
Zeng, Cheng ; Oren, Nir. / Dynamic taxi pricing. Paper presented at European Conference on Artificial Intelligence (ECAI-2014), Prague, United Kingdom.2 p.
@conference{f9deb55858824b4494082390595d76dd,
title = "Dynamic taxi pricing",
abstract = "Taxi journeys are usually priced according to the distance covered and time taken for the trip. Such a fixed cost strategy is simple to understand, but does not take into account the likelihood that a taxi can pick up additional pas- sengers at the original passenger’s destination. In this paper we investigate dynamic taxi pricing strategies. By using do- main knowledge, such strategies discount trips to locations containing many potential passengers, and increase fares to those areas with few potential passengers. Identifying a closed form optimal dynamic pricing strategy is difficult, and by rep- resenting the domain as an MDP, we can identify an optimal strategy for specific domains. We empirically compare such dynamic pricing strategies with fixed cost strategies, and sug- gest future extensions to this work.",
author = "Cheng Zeng and Nir Oren",
note = "This article is published online with Open Access by IOS Press and distributed under the terms of the Creative Commons Attribution Non-Commercial License. This research is supported by the award made by the RCUK Digital Economy theme to the dot.rural Digital Economy Hub, award reference: EP/G066051/1.; European Conference on Artificial Intelligence (ECAI-2014) ; Conference date: 18-08-2014 Through 22-08-2014",
year = "2014",
month = "8",
doi = "10.3233/978-1-61499-419-0-1135",
language = "English",
pages = "1135--1136",

}

TY - CONF

T1 - Dynamic taxi pricing

AU - Zeng, Cheng

AU - Oren, Nir

N1 - This article is published online with Open Access by IOS Press and distributed under the terms of the Creative Commons Attribution Non-Commercial License. This research is supported by the award made by the RCUK Digital Economy theme to the dot.rural Digital Economy Hub, award reference: EP/G066051/1.

PY - 2014/8

Y1 - 2014/8

N2 - Taxi journeys are usually priced according to the distance covered and time taken for the trip. Such a fixed cost strategy is simple to understand, but does not take into account the likelihood that a taxi can pick up additional pas- sengers at the original passenger’s destination. In this paper we investigate dynamic taxi pricing strategies. By using do- main knowledge, such strategies discount trips to locations containing many potential passengers, and increase fares to those areas with few potential passengers. Identifying a closed form optimal dynamic pricing strategy is difficult, and by rep- resenting the domain as an MDP, we can identify an optimal strategy for specific domains. We empirically compare such dynamic pricing strategies with fixed cost strategies, and sug- gest future extensions to this work.

AB - Taxi journeys are usually priced according to the distance covered and time taken for the trip. Such a fixed cost strategy is simple to understand, but does not take into account the likelihood that a taxi can pick up additional pas- sengers at the original passenger’s destination. In this paper we investigate dynamic taxi pricing strategies. By using do- main knowledge, such strategies discount trips to locations containing many potential passengers, and increase fares to those areas with few potential passengers. Identifying a closed form optimal dynamic pricing strategy is difficult, and by rep- resenting the domain as an MDP, we can identify an optimal strategy for specific domains. We empirically compare such dynamic pricing strategies with fixed cost strategies, and sug- gest future extensions to this work.

U2 - 10.3233/978-1-61499-419-0-1135

DO - 10.3233/978-1-61499-419-0-1135

M3 - Paper

SP - 1135

EP - 1136

ER -