Title: Predictive reinforcement learning algorithm for unstructured business process optimisation: case of human resources process

Authors: Samia Chehbi Gamoura

Addresses: HuManiS (UR 7308), EM Strasbourg Business School, Strasbourg University, France

Abstract: While many companies have agreed on business process management to deal with the collaborative and transversal activities, research efforts remain in premature junctures where some technical defies persevere, particularly in the unstructured business processes (UBP). This paper has a threefold purpose: decreasing the unexpected actions in processes, reducing the time-consuming of tasks, and increasing the availability of service during the execution. This paper's research sheds a new insight into UBP, where mutations remain poorly understood in the academic literature but seem to lag behind industrial applications' progress. The methodology proposes a new variant of reinforcement learning based on a version-oriented algorithm to predict the best action to undertake. The experimentation includes validation on an industrial case study about the human resources process of recruitment. Besides, this research provides an in-depth research analysis about the topic to be considered, at least, as a research background for further research works.

Keywords: unstructured business process; UBP; prediction; machine learning; reinforcement learning.

DOI: 10.1504/IJSTDS.2021.116969

International Journal of Spatio-Temporal Data Science, 2021 Vol.1 No.2, pp.184 - 214

Received: 01 Dec 2020
Accepted: 26 Dec 2020

Published online: 10 Aug 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article