Zone-Agnostic Greedy Taxi Dispatch Algorithm Based on Contextual Matching Matrix for Efficient Maximization of Revenue and Profit

This paper addresses the taxi fleet dispatch problem, which is critical for many transport service platforms such as Uber, Lyft, and Didi Chuxing. We focus on maximizing the revenue and profit a taxi platform can generate through the dispatch approaches designed with various criteria. We consider de...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Youngrae Kim, Young Yoon
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	taxi dispatching greedy algorithm reinforcement learning contextual matching Electronics TK7800-8360
Acceso en línea:	https://doaj.org/article/d62710e050a641e99e47263945580b23
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d62710e050a641e99e47263945580b23
record_format	dspace
spelling	oai:doaj.org-article:d62710e050a641e99e47263945580b232021-11-11T15:39:19ZZone-Agnostic Greedy Taxi Dispatch Algorithm Based on Contextual Matching Matrix for Efficient Maximization of Revenue and Profit10.3390/electronics102126532079-9292https://doaj.org/article/d62710e050a641e99e47263945580b232021-10-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/21/2653https://doaj.org/toc/2079-9292This paper addresses the taxi fleet dispatch problem, which is critical for many transport service platforms such as Uber, Lyft, and Didi Chuxing. We focus on maximizing the revenue and profit a taxi platform can generate through the dispatch approaches designed with various criteria. We consider determining the proportion of taxi fleets to different destination zones given the expected rewards from the future states following the distribution decisions learned through reinforcement learning (RL) algorithms. We also take into account more straightforward greedy algorithms that look ahead fewer decision time steps in the future. Our dispatch decision algorithms commonly leverage contextual information and heuristics using a data structure called Contextual Matching Matrix (CMM). The key contribution of our paper is the insight into the trade-off between different design criteria. Primarily, through the evaluation with actual taxi operation data offered by Seoul Metropolitan Government, we challenge the natural expectation that the RL-based approaches yield the best result by showing that a lightweight greedy algorithm can have a competitive advantage. Moreover, we break the norm of dissecting the service area into sub-zones and show that matching passengers beyond arbitrary boundaries generates significantly higher operating income and profit.Youngrae KimYoung YoonMDPI AGarticletaxi dispatchinggreedy algorithmreinforcement learningcontextual matchingElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2653, p 2653 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	taxi dispatching greedy algorithm reinforcement learning contextual matching Electronics TK7800-8360
spellingShingle	taxi dispatching greedy algorithm reinforcement learning contextual matching Electronics TK7800-8360 Youngrae Kim Young Yoon Zone-Agnostic Greedy Taxi Dispatch Algorithm Based on Contextual Matching Matrix for Efficient Maximization of Revenue and Profit
description	This paper addresses the taxi fleet dispatch problem, which is critical for many transport service platforms such as Uber, Lyft, and Didi Chuxing. We focus on maximizing the revenue and profit a taxi platform can generate through the dispatch approaches designed with various criteria. We consider determining the proportion of taxi fleets to different destination zones given the expected rewards from the future states following the distribution decisions learned through reinforcement learning (RL) algorithms. We also take into account more straightforward greedy algorithms that look ahead fewer decision time steps in the future. Our dispatch decision algorithms commonly leverage contextual information and heuristics using a data structure called Contextual Matching Matrix (CMM). The key contribution of our paper is the insight into the trade-off between different design criteria. Primarily, through the evaluation with actual taxi operation data offered by Seoul Metropolitan Government, we challenge the natural expectation that the RL-based approaches yield the best result by showing that a lightweight greedy algorithm can have a competitive advantage. Moreover, we break the norm of dissecting the service area into sub-zones and show that matching passengers beyond arbitrary boundaries generates significantly higher operating income and profit.
format	article
author	Youngrae Kim Young Yoon
author_facet	Youngrae Kim Young Yoon
author_sort	Youngrae Kim
title	Zone-Agnostic Greedy Taxi Dispatch Algorithm Based on Contextual Matching Matrix for Efficient Maximization of Revenue and Profit
title_short	Zone-Agnostic Greedy Taxi Dispatch Algorithm Based on Contextual Matching Matrix for Efficient Maximization of Revenue and Profit
title_full	Zone-Agnostic Greedy Taxi Dispatch Algorithm Based on Contextual Matching Matrix for Efficient Maximization of Revenue and Profit
title_fullStr	Zone-Agnostic Greedy Taxi Dispatch Algorithm Based on Contextual Matching Matrix for Efficient Maximization of Revenue and Profit
title_full_unstemmed	Zone-Agnostic Greedy Taxi Dispatch Algorithm Based on Contextual Matching Matrix for Efficient Maximization of Revenue and Profit
title_sort	zone-agnostic greedy taxi dispatch algorithm based on contextual matching matrix for efficient maximization of revenue and profit
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/d62710e050a641e99e47263945580b23
work_keys_str_mv	AT youngraekim zoneagnosticgreedytaxidispatchalgorithmbasedoncontextualmatchingmatrixforefficientmaximizationofrevenueandprofit AT youngyoon zoneagnosticgreedytaxidispatchalgorithmbasedoncontextualmatchingmatrixforefficientmaximizationofrevenueandprofit
_version_	1718434700405506048

Zone-Agnostic Greedy Taxi Dispatch Algorithm Based on Contextual Matching Matrix for Efficient Maximization of Revenue and Profit

Ejemplares similares