1. 7 mei 2018
Process Mining in CSCW Systems All truths are easy to understand once they are discovered; the point is to discover them. Galileo Galilei ( ) 1
Prof.dr.ir. Wil van der Aalst
Eindhoven University of Technology
Department of Information Systems
P.O. Box 513, 5600 MB Eindhoven
The Netherlands

2. Outline CSCW spectrum Process Mining ProM Conclusion spectrum
7 mei 2018
Outline
CSCW spectrum
spectrum
motivation
Process Mining
overview
a concrete algorithm: the alpha algorithm
ProM
Architecture
Convertors ( , Staffware, InConcert, SAP, etc.)
Process mining plug-ins
Analysis plug-ins
Conformance testing plug-in
LTL checker plug-in
Social network plug-in
Conclusion

3. we want to apply process mining to each of these domains ...
CSCW spectrum
we want to apply process mining to each of these domains ...

4. process mining is relevant across the whole spectrum

5. Motivation
BAM (Business Activity Monitoring), BOM (Business Operations Management), BPI (Business Process Intelligence) illustrate the interest in process improvement based on monitoring data.
Systems need to be adaptive and self-managing thus increasing the need for monitoring.
Legislation such as the Sarbanes-Oxley Act, is forcing organizations to monitor activities and processes.
Technology push: The data is there and more will come! (cf. ERP systems, RFID, webservices, etc.).

6. Process Mining

8. Motivation: Reversing the process
process mining
Process mining can be used for:
Process discovery (What is the process?)
Delta analysis (Are we doing what was specified?)
Performance analysis (How can we improve?)

9. Overview www.processmining.org If …then … 2) process model
3) organizational model
4) social network
1) basic performance metrics
5) performance characteristics
6) auditing/security
If …then …

10. Let us focus on mining process models …
3) organizational model
4) social network
1) basic performance metrics
5) performance characteristics
6) auditing/security
If …then …
... and a very simple approach: The alpha algorithm

11. Alpha algorithm α

12. Process log Minimal information in log: case id’s and task id’s.
case 1 : task A
case 2 : task A
case 3 : task A
case 3 : task B
case 1 : task B
case 1 : task C
case 2 : task C
case 4 : task A
case 2 : task B
case 2 : task D
case 5 : task E
case 4 : task C
case 1 : task D
case 3 : task C
case 3 : task D
case 4 : task B
case 5 : task F
case 4 : task D
Minimal information in log: case id’s and task id’s.
Additional information: event type, time, resources, and data.
In this log there are three possible sequences:
ABCD
ACBD EF

13. >,,||,# relations
case 1 : task A
case 2 : task A
case 3 : task A
case 3 : task B
case 1 : task B
case 1 : task C
case 2 : task C
case 4 : task A
case 2 : task B
case 2 : task D
case 5 : task E
case 4 : task C
case 1 : task D
case 3 : task C
case 3 : task D
case 4 : task B
case 5 : task F
case 4 : task D
A>B
A>C
B>C
B>D
C>B
C>D
E>F
Direct succession: x>y iff for some case x is directly followed by y.
Causality: xy iff x>y and not y>x.
Parallel: x||y iff x>y and y>x
Choice: x#y iff not x>y and not y>x.
B||C
C||B
AB
AC
BD
CD
EF

14. Basic idea (1)
xy

15. Basic idea (2)
xy, xz, and y||z

16. Basic idea (3)
xy, xz, and y#z

17. Basic idea (4)
xz, yz, and x||y

18. Basic idea (5)
xz, yz, and x#y

19. It is not that simple: Basic alpha algorithm
Let W be a workflow log over T. a(W) is defined as follows.
TW = { t Î T  |  $s Î W t Î s},
TI = { t Î T  |  $s Î W t = first(s) },
TO = { t Î T  |  $s Î W t = last(s) },
XW = { (A,B) |  A Í TW  Ù B Í TW  Ù  "a Î A"b Î B a ®W b   Ù  "a1,a2 Î A a1#W a2  Ù  "b1,b2 Î B b1#W b2 },
YW = { (A,B) Î X  |  "(A¢,B¢) Î XA Í A¢ ÙB Í B¢Þ (A,B) = (A¢,B¢) },
PW = { p(A,B)  |  (A,B) Î YW } È{iW,oW},
FW = { (a,p(A,B))  |  (A,B) Î YW  Ù a Î A }  È { (p(A,B),b)  |  (A,B) Î YW  Ù b Î B }  È{ (iW,t)  |  t Î TI}  È{ (t,oW)  | t Î TO}, and
a(W) = (PW,TW,FW).
The alpha algorithm has been proven to be correct for a large class of free-choice nets.

20. Example W a(W) case 1 : task A case 2 : task A case 3 : task A
case 3 : task B
case 1 : task B
case 1 : task C
case 2 : task C
case 4 : task A
case 2 : task B
case 2 : task D
case 5 : task E
case 4 : task C
case 1 : task D
case 3 : task C
case 3 : task D
case 4 : task B
case 5 : task F
case 4 : task D
a(W)

21. DEMO Alpha algorithm
48 cases
16 performers

22. ProM framework

23. ProM

24. Converter plug-in: EMailAnalyzer

25. XML format

26. ProM architecture

27. Mining plug-in: Alpha algorithm

28. Mining plug-in: Genetic Miner

29. Approach

30. Mining plug-in: Multi-phase mining

31. Step 1: Get instances

32. Step 2: Project

33. Step 3: Aggregate

34. Step 4: Map onto EPC

35. Step 5: Map onto Petri net (or other language)

36. Mining plug-in: Social network miner

38. Cliques

39. SN based on hand-over of work metric
density of network is 0.225

40. SN based on working together (and ego network)

41. Analysis plug-in: LTL checker

43. Analysis plug-in: Conformance checker
Do they agree?

45. Fitness is not enough

46. Screenshot
(Also runs on Mac.)

47. Other analysis plug-ins

48. More demos?

49. Conclusion
Process mining provides many interesting challenges for scientists, customers, users, managers, consultants, and tool developers.
Interesting across the whole CSCW spectrum.
Get ProM-ed!
You can contribute by applying ProM and developing plug-ins.

50. Thanks to Ton Weijters, Boudewijn van Dongen, Ana Karla Alves de Medeiros, Minseok Song, Laura Maruster, Eric Verbeek, Monique Jansen-Vullers, Hajo Reijers, Michael Rosemann, Anne Rozinat, Christian Guenther Peter van den Brand, Huub de Beer, Andrey Nikolov, et al. for their on-going work on process mining.

51. BPM 2005, Sept., Nancy France http://bpm2005.loria.fr/
More information
BPM 2005, Sept., Nancy France