Work

FairAssign: Stochastically Fair Driver Assignment in Gig Delivery Platforms

Year: 2023
Type: conference-paper
Abstract: Increasing adoption of online commerce has created income opportunities for millions of delivery drivers who deliver items, from clothes and smartphones to foods and medicines, to customers. Despite their indispensability for the ecosystem, the drivers are often deprived of employment benefits and their earnings are tied to the number of successful deliveries, forcing them to go on repeated strikes to demand fair wage. In addition to low wages, there is considerable variability in driver incomes. One major component contributing to this variability is the static assignment of drivers to delivery zones as different zones likely have different workloads and hence earning opportunities. To reduce this variability, we directly engage with the gig delivery drivers to understand their perspectives on fair income distribution, and incorporate the same by proposing FairAssign for dynamic assignment of drivers to delivery zones to ensure fair distribution of earning opportunities.
Authors: Daman Deep Singh, Syamantak Das, Abhijnan Chakraborty
Language: English
Open Access status: bronze
OpenAlex ID: W4380319451
FWCI: 4.752
Cites: 36
Cited by: 5
Related to: 10