Real-time Prediction and Synchronization of Business Process Instances using Data and Control Perspective

Abstract

Nowadays, in a competitive and dynamic environment of businesses, organizations need to moni-<br />tor, analyze and improve business processes with the use of Business Process Management Systems<br />(BPMSs). Management, prediction and time control of events in BPMS is one of the major chal-<br />lenges of this area of research that has attracted lots of researchers. In this paper, we present a<br />4-phase pipeline approach to the problem of synchronizing each pair of dependent process instances<br />to arrive at the corresponding pair of tasks simultaneous or near-simultaneous. In the rst phase,<br />the process model is mined from the event log and enriched by the probabilistic distributions of<br />time information. In the second phase, the hidden processing dependency between the each pair of<br />dependent process instances is formally de ned and is mined from the event log. In the third phase,<br />a process state prediction algorithm is presented to predict the future route of process instance and<br />then predict the remaining time of the process instance to a given point in a predicted route of the<br />business process. In the fourth phase, an iterative synchronization algorithm is presented based on<br />the presented process state prediction algorithm to make each pair of dependent process instances<br />arrive at the corresponding pair of tasks simultaneous or near-simultaneous. Experimental results<br />on a real-life event log of BPI challenge 2012 show that the proposed method leads to 39% reduction<br />in cycle time for dependent process instances.