Process Mining (eBook)

Data Science in Action

Wil M. P. van der Aalst (Autor)

eBook Download: PDF

2016 | 2nd ed. 2016
XIX, 467 Seiten
Springer Berlin (Verlag)
978-3-662-49851-4 (ISBN)

Infos

This is the second edition of Wil van der Aalst's seminal book on process mining, which now discusses the field also in the broader context of data science and big data approaches. It includes several additions and updates, e.g. on inductive mining techniques, the notion of alignments, a considerably expanded section on software tools and a completely new chapter of process mining in the large. It is self-contained, while at the same time covering the entire process-mining spectrum from process discovery to predictive analytics.

After a general introduction to data science and process mining in Part I, Part II provides the basics of business process modeling and data mining necessary to understand the remainder of the book. Next, Part III focuses on process discovery as the most important process mining task, while Part IV moves beyond discovering the control flow of processes, highlighting conformance checking, and organizational and time perspectives. Part V offers a guide to successfully applying process mining in practice, including an introduction to the widely used open-source tool ProM and several commercial products. Lastly, Part VI takes a step back, reflecting on the material presented and the key open challenges. 

Overall, this book provides a comprehensive overview of the state of the art in process mining. It is intended for business process analysts, business consultants, process managers, graduate students, and BPM researchers.

Wil van der Aalst is a full professor at the Department of Mathematics & Computer Science of the Technische Universiteit Eindhoven (TU/e), The Netherlands, where he chairs the Architecture of Information Systems (AIS) group and serves as the scientific director of the Data Science Center Eindhoven. He also has a part-time appointment in the BPM group of Queensland University of Technology (QUT), Australia. His research and teaching interests include information systems, business process management, process modeling, Petri nets, process mining, and simulation.

Wil has published more than 180 journal papers, 19 books, 425 refereed conference or workshop publications, and 60 book chapters. Many of his papers are highly cited (he has a H-index of more than 123 according to Google Scholar, the highest among all European computer scientists) and his ideas on process support have influenced researchers, software developers, and standardization committees worldwide.

Inhalt

Process Mining 3
Preface 6
Acknowledgements 9
Contents 13
Part I: Introduction 18
Chapter 1: Data Science in Action 20
1.1 Internet of Events 20
1.2 Data Scientist 27
1.3 Bridging the Gap Between Process Science and Data Science 32
1.4 Outlook 37
Chapter 2: Process Mining: The Missing Link 41
2.1 Limitations of Modeling 41
2.2 Process Mining 46
2.3 Analyzing an Example Log 51
2.4 Play-In, Play-Out, and Replay 57
2.5 Positioning Process Mining 60
2.5.1 How Process Mining Compares to BPM 60
2.5.2 How Process Mining Compares to Data Mining 62
2.5.3 How Process Mining Compares to Lean Six Sigma 62
2.5.4 How Process Mining Compares to BPR 65
2.5.5 How Process Mining Compares to Business Intelligence 65
2.5.6 How Process Mining Compares to CEP 66
2.5.7 How Process Mining Compares to GRC 66
2.5.8 How Process Mining Compares to ABPD, BPI, WM, … 67
2.5.9 How Process Mining Compares to Big Data 68
Part II: Preliminaries 69
Chapter 3: Process Modeling and Analysis 71
3.1 The Art of Modeling 71
3.2 Process Models 73
3.2.1 Transition Systems 74
3.2.2 Petri Nets 75
3.2.3 Work?ow Nets 81
3.2.4 YAWL 82
3.2.5 Business Process Modeling Notation (BPMN) 84
3.2.6 Event-Driven Process Chains (EPCs) 86
3.2.7 Causal Nets 88
3.2.8 Process Trees 94
3.3 Model-Based Process Analysis 99
3.3.1 Veri?cation 99
3.3.2 Performance Analysis 101
3.3.3 Limitations of Model-Based Analysis 104
Chapter 4: Data Mining 105
4.1 Classi?cation of Data Mining Techniques 105
4.1.1 Data Sets: Instances and Variables 106
4.1.2 Supervised Learning: Classi?cation and Regression 108
4.1.3 Unsupervised Learning: Clustering and Pattern Discovery 110
4.2 Decision Tree Learning 110
4.3 k-Means Clustering 116
4.4 Association Rule Learning 120
4.5 Sequence and Episode Mining 123
4.5.1 Sequence Mining 123
4.5.2 Episode Mining 125
4.5.3 Other Approaches 127
4.6 Quality of Resulting Models 128
4.6.1 Measuring the Performance of a Classi?er 129
4.6.2 Cross-Validation 131
4.6.3 Occam's Razor 134
Part III: From Event Logs to Process Models 138
Chapter 5: Getting the Data 140
5.1 Data Sources 140
5.2 Event Logs 143
5.3 XES 153
5.4 Data Quality 159
5.4.1 Conceptualizing Event Logs 160
5.4.2 Classi?cation of Data Quality Issues 163
5.4.3 Guidelines for Logging 166
5.5 Flattening Reality into Event Logs 168
Chapter 6: Process Discovery: An Introduction 178
6.1 Problem Statement 178
6.2 A Simple Algorithm for Process Discovery 182
6.2.1 Basic Idea 182
6.2.2 Algorithm 186
6.2.3 Limitations of the alpha-Algorithm 189
6.2.4 Taking the Transactional Life-Cycle into Account 192
6.3 Rediscovering Process Models 193
6.4 Challenges 197
6.4.1 Representational Bias 198
6.4.2 Noise and Incompleteness 200
6.4.2.1 Noise 200
6.4.2.2 Incompleteness 201
6.4.2.3 Cross-Validation 202
6.4.3 Four Competing Quality Criteria 203
6.4.4 Taking the Right 2-D Slice of a 3-D Reality 207
Chapter 7: Advanced Process Discovery Techniques 210
7.1 Overview 210
7.1.1 Characteristic 1: Representational Bias 212
7.1.2 Characteristic 2: Ability to Deal With Noise 213
7.1.3 Characteristic 3: Completeness Notion Assumed 214
7.1.4 Characteristic 4: Approach Used 214
7.1.4.1 Direct Algorithmic Approaches 214
7.1.4.2 Two-Phase Approaches 214
7.1.4.3 Divide-and-Conquer Approaches 215
7.1.4.4 Computational Intelligence Approaches 215
7.1.4.5 Partial Approaches 216
7.2 Heuristic Mining 216
7.2.1 Causal Nets Revisited 216
7.2.2 Learning the Dependency Graph 217
7.2.3 Learning Splits and Joins 220
7.3 Genetic Process Mining 222
7.4 Region-Based Mining 227
7.4.1 Learning Transition Systems 227
7.4.2 Process Discovery Using State-Based Regions 231
7.4.3 Process Discovery Using Language-Based Regions 233
7.5 Inductive Mining 237
7.5.1 Inductive Miner Based on Event Log Splitting 237
7.5.2 Characteristics of the Inductive Miner 244
7.5.3 Extensions and Scalability 248
7.6 Historical Perspective 251
Part IV: Beyond Process Discovery 256
Chapter 8: Conformance Checking 258
8.1 Business Alignment and Auditing 258
8.2 Token Replay 261
8.3 Alignments 271
8.4 Comparing Footprints 278
8.5 Other Applications of Conformance Checking 283
8.5.1 Repairing Models 283
8.5.2 Evaluating Process Discovery Algorithms 284
8.5.3 Connecting Event Log and Process Model 287
Chapter 9: Mining Additional Perspectives 290
9.1 Perspectives 290
9.2 Attributes: A Helicopter View 292
9.3 Organizational Mining 296
9.3.1 Social Network Analysis 297
9.3.2 Discovering Organizational Structures 302
9.3.3 Analyzing Resource Behavior 303
9.4 Time and Probabilities 305
9.5 Decision Mining 309
9.6 Bringing It All Together 312
Chapter 10: Operational Support 316
10.1 Re?ned Process Mining Framework 316
10.1.1 Cartography 318
10.1.2 Auditing 319
10.1.3 Navigation 320
10.2 Online Process Mining 320
10.3 Detect 322
10.4 Predict 326
10.5 Recommend 331
10.6 Processes Are Not in Steady State! 333
10.6.1 Daily, Weekly and Seasonal Patterns in Processes 333
10.6.2 Contextual Factors 333
10.6.3 Concept Drift in Processes 335
10.7 Process Mining Spectrum 336
Part V: Putting Process Mining to Work 337
Chapter 11: Process Mining Software 339
11.1 Process Mining Not Included! 339
11.2 Different Types of Process Mining Tools 341
11.3 ProM: An Open-Source Process Mining Platform 345
11.3.1 Historical Context 345
11.3.2 Example ProM Plug-Ins 347
11.3.3 Other Non-commercial Tools 351
11.3.3.1 PMLAB 351
11.3.3.2 CoBeFra 351
11.3.3.3 RapidProM 352
11.4 Commercial Software 353
11.4.1 Available Products 353
11.4.2 Strengths and Weaknesses 359
11.4.2.1 Limited Support for Concurrency 359
11.4.2.2 Limited Support for Conformance Checking 361
11.4.2.3 Performance Perspective is Well Supported 362
11.4.2.4 Data Perspective Not in Models 362
11.4.2.5 Organizational Perspective 362
11.4.2.6 Growing Support for XES 363
11.4.2.7 Getting Event Data from Other Sources 363
11.4.2.8 Filtering 363
11.4.2.9 No Automatic Clustering 363
11.4.2.10 Reporting and Animation 364
11.4.2.11 Links to Other Tools 365
11.4.2.12 Operational Support 365
11.4.2.13 Scalability 365
11.5 Outlook 366
Chapter 12: Process Mining in the Large 367
12.1 Big Event Data 367
12.1.1 N = All 368
12.1.2 Hardware and Software Developments 370
12.1.2.1 In-Memory Databases and Analytics 373
12.1.2.2 Columnar Databases 374
12.1.2.3 Large-Scale Distributed File Systems 375
12.1.3 Characterizing Event Logs 378
12.2 Case-Based Decomposition 382
12.2.1 Conformance Checking Using Case-Based Decomposition 383
12.2.2 Process Discovery Using Case-Based Decomposition 384
12.3 Activity-Based Decomposition 387
12.3.1 Conformance Checking Using Activity-Based Decomposition 388
12.3.2 Process Discovery Using Activity-Based Decomposition 390
12.4 Process Cubes 392
12.5 Streaming Process Mining 395
12.6 Beyond the Hype 398
Chapter 13: Analyzing "Lasagna Processes" 400
13.1 Characterization of "Lasagna Processes" 400
13.2 Use Cases 404
13.3 Approach 405
13.3.1 Stage 0: Plan and Justify 406
13.3.2 Stage 1: Extract 408
13.3.3 Stage 2: Create Control-Flow Model and Connect Event Log 408
13.3.4 Stage 3: Create Integrated Process Model 409
13.3.5 Stage 4: Operational Support 409
13.4 Applications 410
13.4.1 Process Mining Opportunities per Functional Area 410
13.4.2 Process Mining Opportunities per Sector 411
13.4.3 Two Lasagna Processes 415
13.4.3.1 RWS Process 415
13.4.3.2 WOZ Process 417
Chapter 14: Analyzing "Spaghetti Processes" 423
14.1 Characterization of "Spaghetti Processes" 423
14.2 Approach 427
14.3 Applications 430
14.3.1 Process Mining Opportunities for Spaghetti Processes 430
14.3.2 Examples of Spaghetti Processes 432
14.3.2.1 ASML 432
14.3.2.2 Philips Healthcare 433
14.3.2.3 AMC Hospital 436
Part VI: Re?ection 440
Chapter 15: Cartography and Navigation 442
15.1 Business Process Maps 442
15.1.1 Map Quality 443
15.1.2 Aggregation and Abstraction 443
15.1.3 Seamless Zoom 445
15.1.4 Size, Color, and Layout 449
15.1.5 Customization 451
15.2 Process Mining: TomTom for Business Processes? 452
15.2.1 Projecting Dynamic Information on Business Process Maps 452
15.2.2 Arrival Time Prediction 455
15.2.3 Guidance Rather than Control 455
Chapter 16: Epilogue 457
16.1 Process Mining as a Bridge Between Data Mining and Business Process Management 457
16.2 Challenges 459
16.3 Start Today! 461
References 463
Index 473

Produkt-Details

• Erscheint lt. Verlag: 15.4.2016
• Zusatzinfo: XIX, 467 p. 250 illus., 13 illus. in color.
• Verlagsort: Berlin
• Sprache: englisch
• Themenwelt: Mathematik / Informatik ► Informatik ► Programmiersprachen / -werkzeuge
• Themenwelt: Mathematik / Informatik ► Informatik ► Software Entwicklung
• Themenwelt: Wirtschaft ► Betriebswirtschaft / Management ► Wirtschaftsinformatik
• Schlagworte: Big Data • Business Information Systems • Business Intelligence • business process management • Data Mining • Data Science • Workflow Management
• ISBN-10: 3-662-49851-0 / 3662498510
• ISBN-13: 978-3-662-49851-4 / 9783662498514