Optimized Execution of Business Processes on Crowdsourcing Platforms

Crowdsourcing in enterprises is a promising approach for organizing a flexible workforce. Recent developments show that the idea gains additional momentum. However, an obstacle for widespread adoption is the lack of an integrated way to execute business processes based on a crowdsourcing platform. The main difference compared to traditional approaches in business process execution is that tasks or activities cannot be directly assigned but are posted to the crowdsourcing platform, while people can choose deliberately which tasks to book and work on. In this paper we propose a framework for adaptive execution of business processes on top of a crowdsourcing platform. Based on historical data gathered by the platform we mine the booking behavior of people based on the nature and incentive of the crowdsourced tasks. Using the learned behavior model we derive an incentive management approach based on mathematical optimization that executes business processes in a cost-optimal way considering their deadlines. We evaluate our approach through simulations to prove the feasibility and effectiveness. The experiments verify our assumptions regarding the necessary ingredients of the approach and show the advantage of taking the booking behavior into account compared to the case when it is partially of fully neglected.