Apromore: Advanced Business Process Analytics on the Cloud

1. Apromore: Advanced Open-Source Process Analytics on the Cloud Raffaele Conforti • School of Computing & Information Systems The University of Melbourne, Australia Marlon Dumas • Institute of Computer Science University of Tartu, Estonia 1

2. Process discovery Process analysis Process redesign Process implementation Process monitoring Process identification Process architecture As-is process model Insights on issues and their impact To-be process model Executable process model/ change management plan Conformance and performance insights Business Process Analytics (Tools & Methods) Business Process Management  Monitoring

3. Statistics-Based Techniques Performance Dashboards Model-Based Techniques Process Mining Database Enterprise System Business Process Analytics Event log Event stream 3

4. Process Mining 4

5. Open-source • Apromore • U. Melbourne, U. Tartu, … • bupaR • U. Hasselt • ProM • TU/e Lightweight • Disco • QPR Xpress Enterprise-level • Celonis • Minit • myInvenio • ProcessGold • QPR • Signavio PI • … 5 Process Mining Tools: Overview 5

6. Apromore – Advanced Process Analytics Platform • Open-source BPM analytics platform • Available as a Web-based application, running on desktop or cloud • 50+ (really working) plugins 6

7. Performance Dashboards Process Mining Database Enterprise System Business Process Analytics Event log Event stream 7

8. Process Mining 8

9. Enter Loan Application Retrieve Applicant Data Compute Installments Approve Simple Application Approve Complex Application Notify Rejection Notify Eligibility Directly-follows graph (process map) Process model (e.g. BPMN) Automated process discovery Discover a model of the business process live data historical data Social network

10. Process Maps A dependency graph of a log is a graph where: • Each activity is represented by one node • An arc from activity A to activity B means that B is directly followed by A in at least one trace in the log Arcs in a dependency graph may be annotated with: • Absolute frequency: How many times B directly follows A? • Relative frequency: What percentage of times A is directly followed by B? • Time: What is the average time between the occurrence of A and the occurrence of B? 10

11. To cope with complex logs, process maps are used together with two operators: 1. Abstract the process map: • Show only most frequent activities • Show only most frequent arcs 2. Filter the traces in the event log • Remove all events that fulfil a condition • Remove traces that fulfil a condition Abstraction and Filtering 11

12. Alpha miner (α-miner) • Simple, limited, not robust Heuristics miner • Robust to noise, fast, but can produce incorrect models Inductive miner • Ensures that models are block-structured & correct Split miner • Produces deadlock-free but not necessarily structured models Discovering BPMN Process Models 12

13. Automated Process Discovery Methods Heuristics Miner good F-score complex models semantic errors 13 Inductive Miner high fitness no semantic errors simpler models low precision A. Augusto et al. Split Miner: Discovering Accurate and Simple Business Process Models from Event Logs. In ICDM’2017. Split Miner high fitness no semantic errors simpler models Moderate precision

14. Demo Time!

15. 15 Process Mining

16. 16 ≠ Conformance Checking Given a process model and an event log, find, describe, and/or measure the differences between them

17. Unfitting behaviour: • Task C is optional (i.e. may be skipped) in the log Additional behavior: • The cycle including IGDF is not observed in the log Event log: ABCDEH ACBDEH ABCDFH ACBDFH ABDEH ABDFH Conformance Checking 17 García-Bañuelos et al. “Complete and Interpretable Conformance Checking of Business Processes” IEEE Transactions on Software Engineering 44(3): 262-290, 2018

18. Interactive Model Repair A. Armas Cervantes et al. “Interactive and Incremental Business Process Model Repair”, Proceedings of CoopIS’2017

19. 19 Process Model Log Unfitting behavior (lack of fitness) Additional behavior (lack of precision) Lack of generalization Accuracy of Automated Process Discovery

20. Demo Time!

22. Given two logs, find the differences and root causes for variation between the two logs Variants Analysis 22 ≠

23. • Model comparison • Log delta analysis Variants Analysis 23 Model Comparison L1 - Short stay 448 cases 7329 events L2 - Long stay 363 cases 7496 events Log Delta Analysis In L1, “Nursing Primary Assessment” is repeated after “Medical Assign” and “Triage Request”, while in L2 it is not… N. van Beest et al. “Log Delta Analysis: Interpretable Differencing of Business Process Event Logs” Proc. of BPM’2015

24. • Detect process changes and pinpoint the time periods at which they occurred. Drift Detection Log: ABCDF, ABDCF, ADBEDCF, ABDECDF, ABCDEDEDF, ABDCF, AGBCDF, AGBDCF, AGDBEDCF, AGBDECDF, AGBCDEDED F, AGBDCF, Drift

25. Drift Detection

26. Demo Time!

28. Dotted charts Timeline diagrams Performance-enhanced dependency graphs Performance Mining 28

29. Demo Time!

30. Statistics-Based Techniques Performance Dashboards Model-Based Techniques Process Mining Database Enterprise System Business Process Analytics Event log Event stream 30 30

31. Process Dashboards Operational dashboards (runtime) Tactical dashboards (historical) Strategic dashboards (historical) Process Performance Dashboards 31

32. Predictive Process Monitoring Event stream Predictive models Detailed predictive dashboard Alarm-based prescriptive dashboard Aggregate predictive dashboards Event logDatabase Enterprise System 32

33. Predictive Process Monitoring • What is the next activity for this case? • When is this next activity going to take place? • How long is this case still going to take until it is finished? • What is the outcome of this case? • Is the compensation going to be paid? Or rejected? 33

34. Event log Classifier / Regressor / Outcome predictionAttributes Traces 34 Event log Structured predictor Next activity / Future path prediction Attributes Traces Performance measure prediction Predictive Process Monitoring: General Approach

35. Sequence encoding 35

36. Sequence encoding ▷ Index-based encoding ▷ Aggregation encoding ▷ LSTM (not yet in Apromore)

37. Predictive process monitoring workflow Encoding Bucketing Learning Training set Last state Aggregation Index-based … Zero Cluster Prefix-length … Decision tree Random forest SVM … Buckets Models 39

38. • Predict process outcome (e.g. “Is this loan offer going to be rejected?”) • Predict process performance (e.g. “Will this claim take longer than 5 days to be handled?”) • Predict future events (e.g. “What activity is likely to be executed next? And after that?”) Event log Training module Training Validation Predictor Dashboard Runtime module Information system Predictions Stream (Kafka) Predictive model(s) Event stream Event stream Batched Predictions (CSV) Apromore Predictive process monitoring in Apromore 42

39. Demo Time!

40. / process mining algorithms live data historical data process model differences, root-causes conformance report performance measurements A ⇒ B Apromore in a nutshell 15 4,318 14 14 858 13 7,128 26 3,794 32 31 734 28 6,212 9 1,526 941 4,324 258 186 4,360 4,360 Created 4,360 Waiting for Support 12,587 Waiting for Customer 8,681 Resolved 5,023 Closed 4,360 Waiting for Internal 923 Escalation 42 Waiting for Approval 14 Waiting for Triage 31 Enterprise System predictions Apromore