Fast Forecasting of Unstable Data Streams for On-Demand Service Platforms

Yu Jeffrey Hu; Jeroen Rombouts; Ines Wilms

doi:10.1287/isre.2023.0130

Fast Forecasting of Unstable Data Streams for On-Demand Service Platforms

Yu Jeffrey Hu, Jeroen Rombouts^*, Ines Wilms

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

On-demand service platforms face a challenging problem of forecasting a large collection of high-frequency regional demand data streams that exhibit instabilities. This paper develops a novel forecast framework that is fast and scalable and automatically assesses changing environments without human intervention. We empirically test our framework on a large-scale demand data set from a leading on-demand delivery platform in Europe and find strong performance gains from using our framework against several industry benchmarks across all geographical regions, loss functions, and both pre- and post-COVID periods. We translate forecast gains to economic impacts for this on-demand service platform by computing financial gains and reductions in computing costs.

Original language	English
Number of pages	20
Journal	Information Systems Research
DOIs	https://doi.org/10.1287/isre.2023.0130
Publication status	E-pub ahead of print - 30 May 2024

Keywords

e-commerce
platform econometrics
streaming data
forecast breakdown

Access to Document

10.1287/isre.2023.0130Licence: CC BY

1 Working paper

Fast Forecasting of Unstable Data Streams for On-Demand Service Platforms
Hu, Y. J., Rombouts, J. & Wilms, I., Mar 2023, Cornell University - arXiv, 40 p. (arXiv.org; No. 2303.01887).
Research output: Working paper / Preprint › Working paper

Open Access

Cite this

@article{230065ef1a0143a68c25247f425f8739,

title = "Fast Forecasting of Unstable Data Streams for On-Demand Service Platforms",

abstract = "On-demand service platforms face a challenging problem of forecasting a large collection of high-frequency regional demand data streams that exhibit instabilities. This paper develops a novel forecast framework that is fast and scalable and automatically assesses changing environments without human intervention. We empirically test our framework on a large-scale demand data set from a leading on-demand delivery platform in Europe and find strong performance gains from using our framework against several industry benchmarks across all geographical regions, loss functions, and both pre- and post-COVID periods. We translate forecast gains to economic impacts for this on-demand service platform by computing financial gains and reductions in computing costs.",

keywords = "e-commerce, platform econometrics, streaming data, forecast breakdown",

author = "Hu, {Yu Jeffrey} and Jeroen Rombouts and Ines Wilms",

note = "Data from on-demand delivery platform Stuart and Citi Bike publicly available at https://citibikenyc.com/system-data",

year = "2024",

month = may,

day = "30",

doi = "10.1287/isre.2023.0130",

language = "English",

journal = "Information Systems Research",

issn = "1047-7047",

publisher = "INFORMS",

}

TY - JOUR

T1 - Fast Forecasting of Unstable Data Streams for On-Demand Service Platforms

AU - Hu, Yu Jeffrey

AU - Rombouts, Jeroen

AU - Wilms, Ines

N1 - Data from on-demand delivery platform Stuart and Citi Bike publicly available at https://citibikenyc.com/system-data

PY - 2024/5/30

Y1 - 2024/5/30

N2 - On-demand service platforms face a challenging problem of forecasting a large collection of high-frequency regional demand data streams that exhibit instabilities. This paper develops a novel forecast framework that is fast and scalable and automatically assesses changing environments without human intervention. We empirically test our framework on a large-scale demand data set from a leading on-demand delivery platform in Europe and find strong performance gains from using our framework against several industry benchmarks across all geographical regions, loss functions, and both pre- and post-COVID periods. We translate forecast gains to economic impacts for this on-demand service platform by computing financial gains and reductions in computing costs.

AB - On-demand service platforms face a challenging problem of forecasting a large collection of high-frequency regional demand data streams that exhibit instabilities. This paper develops a novel forecast framework that is fast and scalable and automatically assesses changing environments without human intervention. We empirically test our framework on a large-scale demand data set from a leading on-demand delivery platform in Europe and find strong performance gains from using our framework against several industry benchmarks across all geographical regions, loss functions, and both pre- and post-COVID periods. We translate forecast gains to economic impacts for this on-demand service platform by computing financial gains and reductions in computing costs.

KW - e-commerce

KW - platform econometrics

KW - streaming data

KW - forecast breakdown

U2 - 10.1287/isre.2023.0130

DO - 10.1287/isre.2023.0130

M3 - Article

SN - 1047-7047

JO - Information Systems Research

JF - Information Systems Research

ER -

Fast Forecasting of Unstable Data Streams for On-Demand Service Platforms

Abstract

Keywords

Access to Document

Fingerprint

Research output

Fast Forecasting of Unstable Data Streams for On-Demand Service Platforms

Cite this