Predicting process behavior meets factorization machines. (1st December 2018)

• Record Type: Journal Article
• Authors: Lee, Wai Lam Jonathan; Parra, Denis; Munoz-Gama, Jorge; Sepúlveda, Marcos
• Is Part Of: Expert systems with applications. Volume 112(2018)
• Page Start: 87
• Page End: 98
• Publication Date: 2018-12-01
• Subjects: Recommender systems -- Business process management -- Predictive business process monitoring; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2018.05.035
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: Easy-to-configure model to predict the next event of ongoing cases in a process. Cases are represented as overlapping steps to include sequential information. Model training with negative feedback information improves prediction precision. Experiments show performance comparable to state-of-the-art techniques. Abstract: Predictive business process monitoring methods use datasets of completed cases related to a process to predict the behaviour of running cases. To handle the large amounts of available event data, recent works have turned to deep learning techniques and have achieved fairly accurate results. However, results from these techniques are often difficult to interpret and explain. In the area of Recommender systems, factorization models have been an important class of predictive techniques due to its scalability and ability to infer latent features. Motivated by research in Recommender systems, this paper presents a predictive model that combines matrix factorization techniques from Recommender systems and knowledge from Business Process Management to learn interactions between latent features that can be used to predict the next event of an ongoing case. Evaluation on two real-life datasets from a Dutch Financial Institute and Volvo IT Belgium shows that the approach yields results that are comparable and at times superior to state-of-the-art techniques such as neural networks, yielding at most a precision of 0.87 for next event predictions.