Abstract

In administrative processes, such as financial or governmental processes, humans typically do most of the work and must be allocated to tasks in an efficient manner. Business Process Management Systems can help to do this allocation. The allocation of tasks to people is made complicated by the different authorizations and the varying effectiveness of people for tasks. Moreover, administrative processes operate under substantial uncertainty, as the customer’s journey through the process typically is uncertain upon their arrival. To help solve this problem, this talk presents a theoretical model and a software framework for resource allocation in administrative processes. The presentation proceeds to show several solution methods tailored to address the challenges posed by the model. Specifically, it discusses heuristics, periodic stochastic programming, and deep reinforcement learning. The talk specifically addresses the challenges that are encountered when implementing these solution methods, some of which remain unresolved. By doing so the presentation aims to shed light on promising avenues for future research in this domain. The presentation also presents several tools that can be used to help solve resource allocation problems, including a simulation library with Petri nets and an optimization library.