scholarly journals Complex Symbolic Sequence Clustering and Multiple Classifiers for Predictive Process Monitoring

2016 ◽  
pp. 218-229 ◽  
Author(s):  
Ilya Verenich ◽  
Marlon Dumas ◽  
Marcello La Rosa ◽  
Fabrizio Maria Maggi ◽  
Chiara Di Francescomarino
Keyword(s):  
Process Monitoring ◽  
Symbolic Sequence ◽  
Multiple Classifiers ◽  
Sequence Clustering ◽  
Predictive Process

Encoding resource experience for predictive process monitoring

2021 ◽  
pp. 113669
Author(s):  
Jongchan Kim ◽  
Marco Comuzzi ◽  
Marlon Dumas ◽  
Fabrizio Maria Maggi ◽  
Irene Teinemaa
Keyword(s):  
Process Monitoring ◽  
Predictive Process

scholarly journals Predictive Process Monitoring Methods: Which One Suits Me Best?

2018 ◽  
pp. 462-479 ◽  
Author(s):  
Chiara Di Francescomarino ◽  
Chiara Ghidini ◽  
Fabrizio Maria Maggi ◽  
Fredrik Milani
Keyword(s):  
Process Monitoring ◽  
Monitoring Methods ◽  
Predictive Process

scholarly journals Business Process Models in the Context of Predictive Process Monitoring

2021 ◽  
Vol 28 (1) ◽  
pp. 39-46
Author(s):  
Florian Spree
Keyword(s):  
Process Monitoring ◽  
Business Process ◽  
Process Model ◽  
Academic Research ◽  
Research Area ◽  
Process Models ◽  
Business Process Model ◽  
Business Process Models ◽  
Wide Range ◽  
Predictive Process

Predictive process monitoring is a subject of growing interest in academic research. As a result, an increased number of papers on this topic have been published. Due to the high complexity in this research area a wide range of different experimental setups and methods have been applied which makes it very difficult to reliably compare research results. This paper's objective is to investigate how business process models and their characteristics are used during experimental setups and how they can contribute to academic research. First, a literature review is conducted to analyze and discuss the awareness of business process models in experimental setups. Secondly, the paper discusses identified research problems and proposes the concept of a web-based business process model metric suite and the idea of ranked metrics. Through a metric suite researchers and practitioners can automatically evaluate business process model characteristics in their future work. Further, a contextualization of metrics by introducing a ranking of characteristics can potentially indicate how the outcome of experimental setups will be. Hence, the paper's work demonstrates the importance of business process models and their characteristics in the context of predictive process monitoring and proposes the concept of a tool approach and ranking to reliably evaluate business process models characteristics.

scholarly journals Investigating Social Contextual Factors in Remaining-Time Predictive Process Monitoring—A Survival Analysis Approach

Algorithms ◽  
2020 ◽  
Vol 13 (11) ◽  
pp. 267 ◽  
Author(s):  
Niyi Ogunbiyi ◽  
Artie Basukoski ◽  
Thierry Chaussalet
Keyword(s):  
Survival Analysis ◽  
Process Monitoring ◽  
Contextual Factors ◽  
Survival Function ◽  
Analysis Approach ◽  
Contextual Features ◽  
Monitoring Framework ◽  
Predictive Process ◽  
The Impact ◽  
Remaining Time

Predictive process monitoring aims to accurately predict a variable of interest (e.g., remaining time) or the future state of the process instance (e.g., outcome or next step). The quest for models with higher predictive power has led to the development of a variety of novel approaches. However, though social contextual factors are widely acknowledged to impact the way cases are handled, as yet there have been no studies which have investigated the impact of social contextual features in the predictive process monitoring framework. These factors encompass the way humans and automated agents interact within a particular organisation to execute process-related activities. This paper seeks to address this problem by investigating the impact of social contextual features in the predictive process monitoring framework utilising a survival analysis approach. We propose an approach to censor an event log and build a survival function utilising the Weibull model, which enables us to explore the impact of social contextual factors as covariates. Moreover, we propose an approach to predict the remaining time of an in-flight process instance by using the survival function to estimate the throughput time for each trace, which is then used with the elapsed time to predict the remaining time for the trace. The proposed approach is benchmarked against existing approaches using five real-life event logs and it outperforms these approaches.

scholarly journals ORANGE: Outcome-Oriented Predictive Process Monitoring Based on Image Encoding and CNNs

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 184073-184086
Author(s):  
Vincenzo Pasquadibisceglie ◽  
Annalisa Appice ◽  
Giovanna Castellano ◽  
Donato Malerba ◽  
Giuseppe Modugno
Keyword(s):  
Process Monitoring ◽  
Image Encoding ◽  
Predictive Process

From knowledge-driven to data-driven inter-case feature encoding in predictive process monitoring

2019 ◽  
Vol 84 ◽  
pp. 255-264 ◽  
Author(s):  
Arik Senderovich ◽  
Chiara Di Francescomarino ◽  
Fabrizio Maria Maggi
Keyword(s):  
Process Monitoring ◽  
Data Driven ◽  
Feature Encoding ◽  
Predictive Process ◽  
Case Feature
Sign in / Sign up

Export Citation Format

Share Document