Objectives, scope, and contribution to the main conference :

Workshop programme (tentative):

DM-BPM 2017 - Tentative programme

*****


Business Process Management (BPM) refers to the body of theories, methods and tools to support the design, implementation, execution, monitoring and improvement of organizational business processes. Business processes are pervasive and adopted by organizations in most industries. The redesign of organizational business processes to attain better efficiency and effectiveness is often seen as the principal means for organizations to achieve their strategic objectives.

Execution of business processes more and more is supported by IT systems. These can range from simple accounting software supporting order processing in a manufacturing firm to complex enterprise systems integrated with mobile devices and sensors to track shipping logistics on a global scale. Generally, software systems supporting the different phases of BPM are referred to as PAIS (Process-Aware Information Systems).

During process execution, PAIS are able to collect a large amount of data about business processes. This range from event logs, i.e., traces of the execution of activities, to other data concerning, for instance, the outcomes of a business process execution for clients, the documents manipulated, i.e., created, modified, deleted, by a business process, or information about scheduling and cost of activities and resources in a process.

The large amount of data captured and made available by modern PAIS enables the so-called “evidence-based” BPM. While in fact, decisions about process design or improvement may have been historically based on belief or confidence of senior executives and users, nowadays the same decisions can be based on the “evidence” extracted from process execution data. Evidence from process data can assume different forms depending on the different phases of BPM. In the process design and modeling phase, evidence from data can be used to discover the underlying process model, verify the compliance of existing processes to normative process models, or annotate existing process models with additional information to improve process execution. During process execution and monitoring, evidence from data can be used to provide advanced operational support to process users and decision makers by fine tuning the process execution based on predictions and projections. In the process analysis and improvement phases, evidence can be used to understand issues with the processes and think of possible improvements, possibly anticipating the effect that specific improvement choices may bear on the process.

Data mining and knowledge discovery techniques play a major role in extracting evidence from the data generated by PAIS. In very recent years, research on data mining applications in BPM is increasingly getting traction, beyond traditional process mining applications, to span across the different areas of the typical BPM lifecycle, such as process modelling, execution, analysis, monitoring and improvement. In this context, the aim of this workshop is to bring together researchers and industry experts with a common interest in data mining as a tool for extracting knowledge from data produced by PAIS to produce evidence that can be used along the different phases of BPM. In particular, this workshop is seeking two types of contributions: “foundation” contributions deal with the application and customization of core data mining and knowledge discovery techniques to different phases of BPM; “application” contributions refer to the industrial and large scale application of existing and innovative evidence-based techniques to support BPM in real world scenarios.



Relevant topics for the workshop include (but are not limited to) :


  • Association rule mining in BPM
  • Frequent itemset mining in BPM
  • Decision mining in BPM
  • Classification and feature selection in BPM
  • Clustering in BPM
  • Anomaly detection and risk analysis in BPM
  • Quality of evidence extracted for BPM
  • Mining streaming process data
  • Mining uncertain process data
  • Visual and interactive mining in BPM
  • Industrial applications of evidence-based BPM
  • Case studies about data mining in BPM
  • Innovative applications of evidence from data in BPM
  • Evidence-based prediction in BPM

 

Submitted papers will be evaluated on the basis of significance, originality and technical quality. Each paper will be reviewed by 3 PC members. Outstanding accepted papers improved based on the reviews comments will be included in a LNCS/LNAI Post proceedings of PAKDD published by Springer.

All paper submissions will be handled electronically. Each submitted paper should include an abstract up to 200 words and be no longer than 12 single-spaced pages with 10pt font size. Authors are strongly encouraged to use Springer LNCS/LNAI manuscript submission guidelines for their initial submissions. Word/latex templates are available here. Submissions that do not adhere to the submission guidelines will be rejected and will not enter the review process.
All papers must be submitted electronically through the paper submission system in PDF format only.
The submitted papers must not be previously published anywhere and must not be under consideration by any other conference or journal during the PAKDD review process.

Submissions are made through Easychair
Submission deadline:
January 7 January 14th (extended) at 11.59pm KST 

*****

For the authors of papers rejected from PAKDD2017: 
If you are interested in having your paper considered for the DM-BPM workshop, please contact directly the organisers at dm.bpm.pakdd2017@gmail.com before Friday Feb 3rd

*****

Submitting a paper to the workshop means that the authors agree that at least one author should attend the workshop to present the paper, if the paper is accepted. For no-show authors, their affiliations will receive a notification.



Workshop Organizers :


  •  Marco Comuzzi – Ulsan National Institute of Science and Technology – UNIST (Republic of Korea)

 

  • Youcef Djenouri - Ulsan National Institute of Science and Technology – UNIST (Republic of Korea)


  • Zineb Habbas – Universite’ de Lorraine (France)

For any information, the organisers can be contacted at: dm.bpm.pakdd2017@gmail.com

Programme Committee :


  • Fabrizio Maggi (University of Tartu, Estonia)                                             
  • Anna Wilbik (Eindhoven University of Technology, Netherlands)                  
  • Massimiliano De Leoni (Eindhoven University of Technology, Netherlands)    
  • Johannes De Smedt (Katholieke Universiteit Leuven, Belgium)                  
  • Giovanni Acampora (University of Naples Federico II, Italy)                        
  • Son Tran (CSIRO, Australia)                                                                   
  • Minseok Song (POSTECH, Republic of Korea)                                            
  • Pierluigi Plebani (Politecnico di Milano, Italy)                                             
  • Ladjel Belatreche (LIAS/ISAE-ENSMA, Poitiers, France)                              
  • Peng-Yeng Yin (National Chi Nan University, Taiwan)                                 


Important dates and workshop format :


  • Workshop call for papers: October 21, 2016
  • Workshop paper submission deadline: January 7, 2016 Extended to: January 14th, 2017 (11.59pm KST)
  • Workshop author notification: January 27, 2017 February 3rd, 2017
  • Workshop camera-ready due: February 10, 2017
  • Workshop: TBD (PAKDD conference May 23-26, 2017)