A Fine-Grain Batching-Based Task Allocation Algorithm for Spatial Crowdsourcing

Abstract

Task allocation is a critical issue of spatial crowdsourcing. Although the batching strategy performs better than the real-time matching mode, it still has the following two drawbacks: (1) Because the granularity of the batch size set obtained by batching is too coarse, it will result in poor matching accuracy. However, roughly designing the batch size for all possible delays will result in a large computational overhead. (2) Ignoring non-stationary factors will lead to a change in optimal batch size that cannot be found as soon as possible. Therefore, this paper proposes a fine-grained, batching-based task allocation algorithm (FGBTA), considering non-stationary setting. In the batch method, the algorithm first uses variable step size to allow for fine-grained exploration within the predicted value given by the multi-armed bandit (MAB) algorithm and uses the results of pseudo-matching to calculate the batch utility. Then, the batch size with higher utility is selected, and the exact maximum weight matching algorithm is used to obtain the allocation result within the batch. In order to cope with the non-stationary changes, we use the sliding window (SW) method to retain the latest batch utility and discard the historical information that is too far away, so as to finally achieve refined batching and adapt to temporal changes. In addition, we also take into account the benefits of requesters, workers, and the platform. Experiments on real data and synthetic data show that this method can accomplish the task assignment of spatial crowdsourcing effectively and can adapt to the non-stationary setting as soon as possible. This paper mainly focuses on the spatial crowdsourcing task of ride-hailing.

Applied Decision Focused Learning: An End-to-End Decision System for Task Allocation

“…In the recommendation-allocation scenario, an optimization problem can be modelled as shown in Eq. (1) where the objective function depends on a parameter assumed to be known. Notice that, can be the time taken for a worker to complete a task and is often unknown.…”

“…There is an increasing need for continuous and timely maintenance and operation of infrastructure/equipment to keep the smooth functioning of residential areas and communities. Allocating workers to suitable tasks in a timely manner increases operational efficiency which goes to improve the quality of service for customers as well as workers' experience [1]. Onewo has strong requirements for task allocation since employees have to provide residential, office, and public areas with efficient and timely maintenance, repair, and replacement services each day.…”

“…This work is the first attempt to address this problem as far as we know using a machine learning approach. Related studies that optimize task allocation for urban and community management using machine learning approaches is the spatial crowdsourcing (SC) task allocation problem [1]. In the SC scenario, workers are public participants that have signed up to the SC platform while in our setting, workers are employees of a service management company and outside participants cannot take up tasks.…”