AI Strategy and Concepts Bibliography

WIKINDX Resources

van der Aalst, W. M. (2022). Process mining: A 360 degree overview. In Process Mining Handbook (pp. 3–34).Springer. 
Added by: SijanLibrarian (2022-07-14 08:59:13)   Last edited by: SijanLibrarian (2022-07-14 09:04:06)
Resource type: Book Article
BibTeX citation key: vanderAalst2022
Email resource to friend
View all bibliographic details
Categories: Cognitive Science, Complexity Science, Computer Science, Data Sciences, Decision Theory, General, Mathematics
Subcategories: Analytics, Big data, Forecasting, Informatics, Simulations, Systems theory
Creators: van der Aalst
Publisher: Springer
Collection: Process Mining Handbook
Views: 15/15
Views index: 29%
Popularity index: 7.25%
Abstract
Process mining emerged as a new discipline around the turn of the century. The combi-nation of event data and process models poses interesting scientific problems. Initially,the focus was on the discovery of process models (e.g., Petri nets) from example traces.However, over time the scope of process mining broadened in several directions. Next toprocess discovery, topics such as conformance checking and performance analysis wereadded. Different perspectives were added (e.g., time, resources, roles, costs, and casetypes) to move beyond control-flow models. Along with directly-follows graph (DFGs)and Petri nets, a wide range of process model notations has been explored in the context ofevent data. Examples include declarative process models, process trees, artifact-centricand object-centric process models, UML activity models, and BPMN models. In recentyears, the focus also shifted from backward-looking to forward-looking, connectingprocess mining to neighboring disciplines such as simulation, machine learning, andautomation.Over the past two decades, the discipline did not only expand in terms of scope butalso in terms of adoption and tool support. The first commercial process mining toolsemerged 15 years ago (Futura Process Intelligence, Disco, etc.). Now there are over 40commercial products next to open-source process mining tools such as ProM, PM4Py,and bupaR. The adoption in industry has accelerated in the last five years. In severalregions of the world, most of the larger companies are already using process mining,and the process mining market is expected to double every 18 months in the comingyears.Given the amazing developments in the last two decades, a comprehensive processmining summer school is long overdue. This book contains the core material of the firstSummerSchoolonProcessMiningorganizedbytheIEEETaskForceonProcessMining.The Task Force on Process Mining was established in October 2009 as part of the IEEEComputational Intelligence Society. Its activities led to the International Process MiningConference (ICPM) series, a range of successful workshops (BPI, ATAED, PODS4H,etc.), the Process Mining Manifesto (translated into 15+ languages), the XES standard,publicly available datasets, online courses, and case studies. However, a dedicated sum-mer school on process mining was missing. Therefore, we started the preparations forthis in 2020. Due to the COVID-19 pandemic, this was delayed by one year, but thisgave us more time to carefully prepare this handbook on process mining.The summer school took place in Aachen, Germany, during July 4–8, 2022. Thelocation of the summer school was the scenic SuperC building with nice views of thecity center and close to the cathedral of Aachen, which was the first UNESCO WorldHeritage site in Germany.The local organization was undertaken by the Process and Data Science (PADS)group at RWTH Aachen University. The event was financially supported by Wil M.P. van der Aalst’s Alexander von Humboldt (AvH) professorship. The event was alsosupported by the RWTH Center for Artificial Intelligence, the Center of ExcellenceInternet of Production (IoP), Celonis, and Springer.viPrefaceThebookstarts witha360-degreeoverview of thefieldof process mining(Chapter 1).This first chapter introduces the basic concepts, the different types of process mining,process modeling notations, and storage formats for events.Chapter 2 presents the foundations of process discovery. It starts with discoveringdirectly-follows graphs from simple event logs and highlighting the challenges. Thenbasic bottom-up and top-down process discovery techniques are presented that producePetri nets and BPMN models.Chapter 3 presents four additional process discovery techniques: an approach basedon state-based regions, an approach based on language-based regions, the split miningapproach, and the log skeleton-based approach.Techniques to discover declarative process models are presented in Chapter 4. Thechapter focuses on discovering declarative specifications from event logs, monitor-ing declarative specifications against running process executions to promptly detectviolations, and reasoning on declarative process specifications.Chapter 5 presents techniques for conformance checking. An overview of the appli-cations of conformance checking and a general framework are presented. The goal is tocompare modeled and observed behavior.Chapter 6 discusses event data in more detail, also describing the data-preprocessingpipeline, standards like XES, and data quality problems.Chapter 7 takes a more applied view and discusses how process mining is used indifferent industries and the efforts involved in creating an event log. The chapter alsolists best practices, illustrated using the order-to-cash (O2C) process in an SAP system.Chapter8introducesanumberoftechniquesforprocessenhancement,includingpro-cess extension and process improvement. For example, it is shown how to add additionalperspectives to a process model.Chapter 9 introduces event knowledge graphs as a means to model multiple entitiesdistributed over different perspectives. It is shown how to construct, query, and aggregateevent knowledge graphs to get insights into complex behaviors.Predictive process monitoring techniques are introduced in Chapter 10. This is thebranch of process mining that aims at predicting the future of ongoing (uncompleted)process executions.Streaming process mining refers to the set of techniques and tools which have thegoal of processing a stream of data (as opposed to a fixed event log). Chapter 11 presentssuch techniques.The topic of responsible process mining is addressed in Chapter 12. The chapter sum-marizes and discusses current approaches that aim to make process mining responsibleby design, using the well-known FACT criteria (Fairness, Accuracy, Confidentiality, andTransparency).Chapter 13 discusses the evolution of the field of process mining, i.e., the transi-tion from process discovery to process execution management. The focus is on drivingbusiness value.Chapter 14 makes the case that healthcare is a very promising application domainfor process mining with a great societal value. An overview of healthcare processes andhealthcare process data is given, followed by a discussion of common use cases.PrefaceviiChapter 15 shows that process mining is a valuable tool for financial auditing. Bothinternal and external audits are introduced, along with the connection between the twoaudits and the application of process mining.Chapter 16 introduces a family of techniques, called robotic process mining, thatdiscover repetitive routines that can be automated using robotic process automation(RPA) technology.Chapter 17 concludes the book with an analysis of the current state of the processmining discipline and outlook on future developments and challenges.
  
wikindx 6.2.2 ©2003-2020 | Total resources: 1373 | Username: -- | Bibliography: WIKINDX Master Bibliography | Style: American Psychological Association (APA) | Database queries: 58 | DB execution: 0.09664 secs | Script execution: 0.11027 secs