Filters








21,842 Hits in 5.0 sec

ProcessTransformer: Predictive Business Process Monitoring with Transformer Network [article]

Zaharah A. Bukhsh, Aaqib Saeed, Remco M. Dijkman
2021 arXiv   pre-print
In this paper, we propose ProcessTransformer, an approach for learning high-level representations from event logs with an attention-based network.  ...  Predictive business process monitoring focuses on predicting future characteristics of a running process using event logs.  ...  Process mining methods have been used to discover, monitor, and improve the business processes by analyzing the process logs.  ... 
arXiv:2104.00721v1 fatcat:jlxhtdp5cnfd5dfdywc6butp6i

Unsupervised Learning Methods for Anomaly Detection and Log Quality Improvement Using Process Event Log

M. Vijayakamal, D Vasumathi
2020 Figshare  
To overcome this problem, a comprehensive framework is proposed for detecting anomalies from business process event logs and rectify anomalies for process enhancement.  ...  The empirical results revealed that the proposed framework improves performance in anomaly detection and process enhancement.  ...  Moreover, it has control over modelling of latent distribution. This can improve representations it makes in the process of detecting anomalies.  ... 
doi:10.6084/m9.figshare.12199643.v1 fatcat:gk7ed6bwhnezlmk2fju6hiat3a

Multivariate Business Process Representation Learning utilizing Gramian Angular Fields and Convolutional Neural Networks [article]

Peter Pfeiffer, Johannes Lahann, Peter Fettke
2021 arXiv   pre-print
In this paper, we propose a novel approach for representation learning of business process instances which can process and combine most perspectives in an event log.  ...  Instead of training a model for one specific task, representation learning is about training a model to capture all useful information in the underlying data and make it accessible for a predictor.  ...  Characteristics of a process instance that are embedded in the data attributes, can improve the performance of predictive models [13] .  ... 
arXiv:2106.08027v1 fatcat:7pxohsnxfrhppajx2skena3dmu

Convolutional Neural Networks in Process Mining and Data Analytics for Prediction Accuracy

Ekene Obodoekwe, Xianwen Fang, Ke Lu
2022 Electronics  
Using image-based data engineering and convolutional neural networks, the next activity in a business process has been forecast in this paper (CNN).  ...  Almost all organizations stored their data in the cloud as event logs over the last few decades.  ...  Advancements in information systems enable the management of an enormous number of event logs for a business process.  ... 
doi:10.3390/electronics11142128 fatcat:6b6qcnujczfvrpftfalkd5k644

A Comparison of Deep-Learning Methods for Analysing and Predicting Business Processes

Ishwar Venugopal, Jessica Tollich, Michael Fairbank, Ansgar Scherp
2021 2021 International Joint Conference on Neural Networks (IJCNN)  
[26] improve the performance of predictive business models by using text-mining techniques on the unstructured data present in event logs.  ...  In this work, we use a new representation for the event-log data and investigated the performance of different variants of a Graph Convolutional Network (GCN) [14] as a successful example of GNNs.  ... 
doi:10.1109/ijcnn52387.2021.9533742 fatcat:au4wqdzolfborltd6ko6swbqlq

A Technique for Determining Relevance Scores of Process Activities using Graph-based Neural Networks [article]

Matthias Stierle, Sven Weinzierl, Maximilian Harl, Martin Matzner
2020 arXiv   pre-print
To improve business processes with respect to performance measures, process analysts require further guidance from the process model.  ...  In this study, we design Graph Relevance Miner (GRM), a technique based on graph neural networks, to determine the relevance scores for process activities with respect to performance measures.  ...  For this, we perform a process-instance-based sampling to consider the process-instance-affiliations of event log entries. For each event log, we perform ten-fold cross-validation.  ... 
arXiv:2008.03110v1 fatcat:ecwdos3twnhc7ep7asbvromxqe

Neural Process Mining: Multi-Headed Predictive Process Analytics in Practice

Felix Oberdorf, Myriam Schaschek, Nikolai Stein, Christoph Flath
2021 European Conference on Information Systems  
Ever growing data availability combined with rapid progress in the field of analytics has laid the foundation for the emergence of Business Process Management in general and Business Process Analytics  ...  Going beyond descriptive process log analysis, manufacturing companies strive to leverage predictive process analytics to generate process-related predictions.  ...  The graph representation is of special interest for process discovery, in particular considering additional disruption events.  ... 
dblp:conf/ecis/OberdorfSSF21 fatcat:iafpp4l4abhvvcc6wv7dqc2htm

An Experimental Analytics on Discovering Work Transference Networks from Workflow Enactment Event Logs

Hyun Ahn, Dinh-Lam Pham, Kwanghoon Pio Kim
2019 Applied Sciences  
Work transference network is a type of enterprise social network centered on the interactions among performers participating in the workflow processes.  ...  As a sanity check for the framework, we carry out a mining experiment on a dataset of real-life event logs by using the implemented system.  ...  Conflicts of Interest: The authors declare no conflict of interest. Appl. Sci. 2019, 9, 2368  ... 
doi:10.3390/app9112368 fatcat:qntktkzd7bde3ijeebdnsfwlx4

Network Representation Learning Algorithm Based on Neighborhood Influence Sequence

Meng Liu, Ziwei Quan, Yong Liu
2020 Asian Conference on Machine Learning  
Experimental results demonstrate that the embedding learned from the proposed NIS model achieve better performance than state-of-the-art methods in various tasks including node classification, link prediction  ...  In experiments, we compare our model with existing NRL models on four real-world datasets.  ...  These comments are usually difficult to cause other reactions, so most of the interaction between user and business in the network is in an isolated state, which leads to poor performance of all models  ... 
dblp:conf/acml/LiuQL20 fatcat:uubvr6v3dbd4hhkfmm4g5vqn2i

Leveraging Multi-view Deep Learning for Next Activity Prediction

Vincenzo Pasquadibisceglie, Annalisa Appice, Giovanna Castellano, Donato Malerba
2021 International Conference on Business Process Management  
This paper describes a predictive process approach that couples multi-view learning and deep learning, in order to gain accuracy by accounting for the variety of information possibly recorded in event  ...  Experiments with benchmark event logs show the accuracy of the proposed approach compared to several recent state-of-the-art methods.  ...  Acknowledgments The research of Vincenzo Pasquadibisceglie is funded by PON RI 2014-2020 -Big Data Analytics for Process Improvement in Organizational Development -CUP H94F18000270006.  ... 
dblp:conf/bpm/Pasquadibisceglie21 fatcat:5qggtenvtraa3hmrszr3qstswm

SA 2019 Placeholder Page

2019 2019 First International Conference on Societal Automation (SA)  
We work on extending this work to exploit strengths of process mining and Bayesian networks to better assure counterfactual explanations.  ...  In this paper we focus on the issue of interpretable decision making in time series data streams.  ...  The business process representation improves the interpretability of the model allowing for easier inspection of the 2 For details on event log format see http://pm4py.org/. model.  ... 
doi:10.1109/sa47457.2019.8938075 fatcat:m5ixqeuzyjatjif244yqakayma

A systematic literature review on state-of-the-art deep learning methods for process prediction

Dominic A. Neu, Johannes Lahann, Peter Fettke
2021 Artificial Intelligence Review  
Given a sequence of events of an ongoing trace, process prediction allows forecasting upcoming events or performance measurements.  ...  AbstractProcess mining enables the reconstruction and evaluation of business processes based on digital traces in IT systems.  ...  The influence differs from event log to event log in their experiment. Consequently, a methodical framework to identify explanatory variables for business processes should be developed.  ... 
doi:10.1007/s10462-021-09960-8 fatcat:cikw2kxd7vhozeevsrl3qp6p24

A systematic literature review on state-of-the-art deep learning methods for process prediction [article]

Dominic A. Neu, Johannes Lahann, Peter Fettke
2021 arXiv   pre-print
Given a sequence of events of an ongoing trace, process prediction allows forecasting upcoming events or performance measurements.  ...  Process mining enables the reconstruction and evaluation of business processes based on digital traces in IT systems. An increasingly important technique in this context is process prediction.  ...  The influence differs from event log to event log in their experiment. Consequently, a methodical framework to identify explanatory variables for business processes should be developed.  ... 
arXiv:2101.09320v2 fatcat:w33pzhynqbh5zbtv55utqiadqq

Cause vs. Effect in Context-Sensitive Prediction of Business Process Instances [article]

Jens Brunk, Matthias Stierle, Leon Papke, Kate Revoredo, Martin Matzner, Jörg Becker
2020 arXiv   pre-print
Predicting undesirable events during the execution of a business process instance provides the process participants with an opportunity to intervene and keep the process aligned with its goals.  ...  We leverage previous work on probabilistic models to develop a Dynamic Bayesian Network technique.  ...  A de-facto standard repository for business process event logs in the domain stems from the Business Processing Intelligence (BPI) Challenges that have been held since 2011.  ... 
arXiv:2007.07549v1 fatcat:fqac45hilvbcpdyopaqhggo6ey

Real‐time business process monitoring using formal concept analysis

Bokyoung Kang, Jae‐Yoon Jung, Nam Wook Cho, Suk‐Ho Kang
2011 Industrial management & data systems  
Design/methodology/approach -FCA is utilized to analyze relations among patterns of events in historical process logs, and this method of data analysis visualizes the relations in a concept lattice.  ...  The proposed method was developed in a prototype system for proof of concept and has been illustrated using a simplified real-world example of a business process in a telecommunications company.  ...  To represent process instances and events in the log, an event history model H is formalized in Table I shows an example of an event history model for the example process in During process execution  ... 
doi:10.1108/02635571111137241 fatcat:pt7rr3qzjbfhtisi67fcs3b76m
« Previous Showing results 1 — 15 out of 21,842 results