What is it about?
This paper is about process mining, that is a research discipline that aims to discover, monitor and improve real processing using event logs. In this paper we tackle the problem of predicting the next activity given a sequence of activities. The proposed method can work on the the Spark parallel computation framework in order to process massive logs.
Featured Image
Photo by Stephen Dawson on Unsplash
Why is it important?
This work is important since the prediction of the next activity is based on a scalable approach that can process big data, namely large event logs. This is possible thanks to a parallel and distributed solution (by exploiting the Spark parallel computation framework) which can make reasonable decisions in the absence of perfect models.
Perspectives
This work is a highly cited work in the area of process mining, defines a general approach, and faces a very practical problem. The background is a solid work on sequence mining.
Prof. Donato Malerba
Universita degli Studi di Bari Aldo Moro
Read the Original
This page is a summary of: Distributed Learning of Process Models for Next Activity Prediction, January 2018, ACM (Association for Computing Machinery),
DOI: 10.1145/3216122.3216125.
You can read the full text:
Contributors
The following have contributed to this page
