An official website of the United States government
Crowdsourced transportation by independent suppliers (or drivers) is central to urban delivery and mobility platforms. While utilizing crowdsourced resources has several advantages, it comes with the challenge that suppliers are not bound to assignments made by the platforms. In practice, suppliers often decline offered service requests, e.g., due to the required travel detour, the expected tip, or the area a request is located. This leads to inconveniences for the platform (ineffective assignments), the corresponding customer (delayed service), and also the suppliers themselves (non-fitting assignment, less revenue). Therefore, the objective of this work is to analyze the impact of a platform approximating and incorporating individual suppliers’ acceptance behavior into the order dispatching process and to quantify its impact on all stakeholders (platform, customers, suppliers). To this end, we propose a dynamic matching problem where suppliers’ acceptances or rejections of offers are uncertain. Suppliers who accept an offered request are assigned and reenter the system after service looking for another offer. Suppliers declining an offer stay idle to wait for another offer, but leave after a limited time if no acceptable offer is made. Every supplier decision reveals only their acceptance or rejection information to the platform, and in this paper, we present a corresponding mathematical model and an approximation method that translates supplier responses into updated approximations of the likelihood of a specific supplier to accept a specific future offer and use this information to optimize subsequent offering decisions. We show via a computational study based on crowdsourced food delivery that online approximation and incorporating individual supplier acceptance estimates into order dispatching leads to overall more successful assignments, more revenue for the platform and most of the suppliers, and less waiting for the customers to be served. We also show that considering individual supplier behavior can lead to unfair treatment of more agreeable suppliers.
more »
« less
A Prescriptive Machine Learning Method for Courier Scheduling on Crowdsourced Delivery Platforms
Crowdsourced delivery platforms face the unique challenge of meeting dynamic customer demand using couriers not employed by the platform. As a result, the delivery capacity of the platform is uncertain. To reduce the uncertainty, the platform can offer a reward to couriers that agree to be available to make deliveries for a specified period of time, that is, to become scheduled couriers. We consider a scheduling problem that arises in such an environment, that is, in which a mix of scheduled and ad hoc couriers serves dynamically arriving pickup and delivery orders. The platform seeks a set of shifts for scheduled couriers so as to minimize total courier payments and penalty costs for expired orders. We present a prescriptive machine learning method that combines simulation optimization for off-line training and a neural network for online solution prescription. In computational experiments using real-world data provided by a crowdsourced delivery platform, our prescriptive machine learning method achieves solution quality that is within 0.2%-1.9% of a bespoke sample average approximation method while being several orders of magnitude faster in terms of online solution generation.
more »
« less
- Award ID(s):
- 2145661
- PAR ID:
- 10482723
- Publisher / Repository:
- INFORMS
- Date Published:
- Journal Name:
- Transportation Science
- Volume:
- 57
- Issue:
- 4
- ISSN:
- 0041-1655
- Page Range / eLocation ID:
- 889-907
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract This paper explores a neglected aspect of platform work: how the spatial mobility that app-based couriers must perform requires them to violate taken-for-granted assumptions that define who belongs where. By assigning tasks during atypical hours and requiring gig workers to use their personal clothing, tools and vehicles, platforms strip delivery workers of signifiers that legitimate their presence in consumers’ neighbourhoods. The result is a condition we call ‘unbelonging’ – a liminal state in which their presence is considered problematic, exposing them to threats of physical and symbolic violence. Our findings, which draw on 45 interviews with parcel delivery workers, contribute to the developing literature on urban geography and the socio-spatial impacts of the platform revolution.more » « less
-
Meal delivery has become increasingly popular in past years and of great importance in past months during the COVID-19 pandemic. Sustaining such services depends on maintaining provider profitability and reduced cost to consumers while continuing to support autonomy and independence for customers, restaurants, and delivery drivers (here crowdsourced drivers). This paper investigates the possible enactment of curbside regulations in the U.S. that limit the number of drivers simultaneously waiting at restaurants to pick up meals for delivery on both public safety and delivery efficiency. Curbside regulations would aim to increase safety by enabling social distancing between delivery personnel at pickup locations and have a secondary benefit of improving local traffic flows, which are sometimes impeded in busier, urban locations. Curbside space limits are studied in relation to their impacts on consumer-related performance measures: freshness of the food on delivery and click-to-door time. This investigation is enabled through a proposed hybrid discrete-event and time-advanced simulation platform that replicates meal delivery service calls and pickup and delivery operations across a region built on data from a leading meal delivery company. Embedded within the simulation is an integer program that optimally assigns orders to drivers in a dynamically changing environment. Order assignments are constrained by imposed curbside capacity limits at the restaurants, and potential efficiencies and curbside violation reductions from bundling orders are assessed. Results of analyses from numerical experiments provide insights to state and local communities in designing curbside restrictions that reduce curbside crowding yet enable delivery companies to retain their profitability.more » « less
-
Network slicing allows mobile network operators to virtualize infrastructures and provide customized slices for supporting various use cases with heterogeneous requirements. Online deep reinforcement learning (DRL) has shown promising potential in solving network problems and eliminating the simulation-to-reality discrepancy. Optimizing cross-domain resources with online DRL is, however, challenging, as the random exploration of DRL violates the service level agreement (SLA) of slices and resource constraints of infrastructures. In this paper, we propose OnSlicing, an online end-to-end network slicing system, to achieve minimal resource usage while satisfying slices' SLA. OnSlicing allows individualized learning for each slice and maintains its SLA by using a novel constraint-aware policy update method and proactive baseline switching mechanism. OnSlicing complies with resource constraints of infrastructures by using a unique design of action modification in slices and parameter coordination in infrastructures. OnSlicing further mitigates the poor performance of online learning during the early learning stage by offline imitating a rule-based solution. Besides, we design four new domain managers to enable dynamic resource configuration in radio access, transport, core, and edge networks, respectively, at a timescale of subseconds. We implement OnSlicing on an end-to-end slicing testbed designed based on OpenAirInterface with both 4G LTE and 5G NR, OpenDayLight SDN platform, and OpenAir-CN core network. The experimental results show that OnSlicing achieves 61.3% usage reduction as compared to the rule-based solution and maintains nearly zero violation (0.06%) throughout the online learning phase. As online learning is converged, OnSlicing reduces 12.5% usage without any violations as compared to the state-of-the-art online DRL solution.more » « less
-
Abstract This article uses data from a natural experiment to address one of the most contentious issues in the on-demand platform economy—whether gig work is compatible with standard employment. We analyze a US-based package delivery platform that shifted a subset of its workers from independent contractors to employees, thereby creating a natural experiment that allowed us to exploit variation over time and across locations. We examine the impact of employment status on work scheduling practices, hours of work and the firm’s ability to match workers’ scheduled hours with the amount of time they were actively engaged in parcel delivery. We find that after the transition to employment, flexibility with respect to how work schedules were determined was maintained, and drivers’ total hours of work increased. We also find that the switch to employee status increased the firm’s ability to match scheduled and actual working time, indicating greater operational efficiency. We conclude, contrary to claims commonly made by platform firms, that employment status can coexist with the platform model.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1287/trsc.2022.1152
