Machine Learning in Mobile Crowd Sourcing: A Behavior-based Recruitment Model

What is it about?

Finding optimal individuals, or workers, from the crowd to successfully complete one or more tasks is one of the main challenges of Mobile Crowd Sourcing (MCS). This work combines numerical attributes (such as reputation and distance to task) with machine learning predictions to perform workers selection. Machine learning is used for behavioral profiling workers in MCS, based on worker-related contexts, such as worker rating and assigned load, and task-related contexts, such as weather and kind of day. Based on the behavioral model, the willingness of a worker to perform given task prior to their selection is predicted.

Featured Image

Photo by Pietro Jeng on Unsplash

Photo by Pietro Jeng on Unsplash

Why is it important?

Most of the existing MCS selection frameworks rely primarily on reputation-based feedback mechanisms to assess the level of commitment of potential workers. Such frameworks select workers having high reputation scores but without any contextual-awareness of the workers, at the time of selection, or the task. This may lead to an unfair selection of workers who will not perform the task. Hence, reputation on its own only gives an approximation of workers’ behaviors since it assumes that workers always behave consistently regardless of the situational context. It has been proven by many experiments that humans tend to show behavioral consistency across similar situations and behave differently in disparate situations. Hence, the behavior of the workers in terms of their commitment towards a task can be predicted based on the experience derived from their past interactions. This work proposes a novel recruitment system in MCS based on behavioral profiling. The proposed approach uses machine learning to predict the probability of the workers performing a given task, based on their learned behavioral models. Simulations based on real-life dataset show that considering human behavior in varying situations improves the Quality of Recruitment achieved by the tasks and their completion confidence.