Discovering Petri Nets: Evidence-Based Business Process Management

Discovering Petri Nets: Evidence-Based Business Process ManagementWil van der Aalst

Carl Adam Petri Memorial Symposium Humboldt-Universität zu BerlinFebruary 4, 2011

Commandeur in de Orde van de Nederlandse Leeuw(Petri net conference 2003 in Eindhoven)

9-2-2011 PAGE 1

About 50 people are Commandeur in de Orde van de Nederlandse Leeuw, e.g., Wim Duisenberg, Gerard 't Hooft, Harry Mulisch, Gerard Reve, Joop den Uyl

Carl Adam Petri (12 July 1926 – 2 July 2010)

• Started a new subfield of computer science.“Much of what I have been saying was already well understood in the

sixties by Carl Adam Petri, who pioneered the scientific modeling of discrete concurrent systems. Petri's work has a secure place at the

root of concurrency theory.” (Robin Milner 1991)

• Guiding principles:- Concurrency as a starting point rather than an

afterthought (locality of actions).- Formalism should be consistent with the laws of

physics.• Researchers in the growing Business Process

Management (BPM) community use these principles.- Modeling languages have Petri-net like semantics.- More and more emphasis on empirical validation.

PAGE 2

PAGE 3

Process Mining

PAGE 4

software system

(process)model

eventlogs

modelsanalyzes

discovery

records events, e.g., messages,

transactions, etc.

specifies configures implements

analyzes

supports/controls

enhancement

conformance

“world”

people machines

organizationscomponents

businessprocesses

Play-Out

PAGE 5

event logprocess model

Play-In

PAGE 6

event log process model

Replay

PAGE 7

event log process model

• extended model showing times, frequencies, etc.

• diagnostics• predictions• recommendations

Simple example log

PAGE 8

Simple control-flow discovery (Play-In)

PAGE 9

astart register

request

bexamine

thoroughly

cexamine casually

d

check ticket

decide

pay compensation

reject request

reinitiate request

e

g

h

f

end

c1

c2

c3

c4

c5

Alpha algorithm

PAGE 10

a b

(a) sequence pattern: a→b

a

b

c

(b) XOR-split pattern:a→b, a→c, and b#c

a

b

c

(c) XOR-join pattern:a→c, b→c, and a#b

a

b

c

(d) AND-split pattern:a→b, a→c, and b||c

a

b

c

(e) AND-join pattern:a→c, b→c, and a||b

Discovering places

PAGE 11

a1

...

a2

am

b1

b2

bn

p(A,B) ...

A={a1,a2, … am} B={b1,b2, … bn}

Challenge

PAGE 12

process discovery

fitness

precisiongeneralization

simplicity

“able to replay event log” “Occam’s razor”

“not overfitting the log” “not underfitting the log”

Example

PAGE 13

astart register

request

bexamine

thoroughly

cexamine casually

dcheck ticket

decide

pay compensation

reject request

reinitiate request

e

g

h

f

end

astart register

request

cexamine casually

dcheckticket

decide reject request

e hend

astart register

request

bexamine thoroughly

cexamine casually

d checkticket

decide

pay compensation

reject request

reinitiate requeste

g

hfend

astart register

request

cexamine casually

dcheckticket

decide reject request

e hend

aregister request

dexamine casually

ccheckticket

decide reject request

e h

a cexamine casually

dcheckticket

decide

e g

a dexamine casually

ccheckticket

decide

e g

register request

register request

pay compensation

pay compensation

aregister request

b dcheckticket

decide reject request

e h

aregister request

d bcheckticket

decide reject request

e h

a b dcheckticket

decide

e gregister request

pay compensation

examine thoroughly

examine thoroughly

examine thoroughly

… (all 21 variants seen in the log)

acdeh

abdeg

adceh

abdeh

acdeg

adceg

adbeh

acdefdbeh

adbeg

acdefbdeh

acdefbdeg

acdefdbeg

adcefcdeh

adcefdbeh

adcefbdeg

acdefbdefdbeg

adcefdbeg

adcefbdefbdeg

adcefdbefbdeh

adbefbdefdbeg

adcefdbefcdefdbeg

455

191

177

144

111

82

56

47

38

33

14

11

9

8

5

3

2

2

1

1

1

# trace

1391

Model 1: Seems right

PAGE 14

acdeh

abdeg

adceh

abdeh

acdeg

adceg

adbeh

acdefdbeh

adbeg

acdefbdeh

acdefbdeg

acdefdbeg

adcefcdeh

adcefdbeh

adcefbdeg

acdefbdefdbeg

adcefdbeg

adcefbdefbdeg

adcefdbefbdeh

adbefbdefdbeg

adcefdbefcdefdbeg

455

191

177

144

111

82

56

47

38

33

14

11

9

8

5

3

2

2

1

1

1

# trace

1391

astart register

request

bexamine

thoroughly

cexamine casually

dcheck ticket

decide

pay compensation

reject request

reinitiate request

e

g

h

f

end

fitness = +precision = +generalization = +simplicity = +

Model 2: Simple and precise, but …

PAGE 15

acdeh

abdeg

adceh

abdeh

acdeg

adceg

adbeh

acdefdbeh

adbeg

acdefbdeh

acdefbdeg

acdefdbeg

adcefcdeh

adcefdbeh

adcefbdeg

acdefbdefdbeg

adcefdbeg

adcefbdefbdeg

adcefdbefbdeh

adbefbdefdbeg

adcefdbefcdefdbeg

455

191

177

144

111

82

56

47

38

33

14

11

9

8

5

3

2

2

1

1

1

# trace

1391

astart register

request

cexamine casually

dcheckticket

decide reject request

e hend

fitness = -precision = +generalization = -simplicity = +

Model 3: Simple but underfitting

PAGE 16

acdeh

abdeg

adceh

abdeh

acdeg

adceg

adbeh

acdefdbeh

adbeg

acdefbdeh

acdefbdeg

acdefdbeg

adcefcdeh

adcefdbeh

adcefbdeg

acdefbdefdbeg

adcefdbeg

adcefbdefbdeg

adcefdbefbdeh

adbefbdefdbeg

adcefdbefcdefdbeg

455

191

177

144

111

82

56

47

38

33

14

11

9

8

5

3

2

2

1

1

1

# trace

1391

astart register

request

bexamine thoroughly

cexamine casually

d checkticket

decide

pay compensation

reject request

reinitiate requeste

g

hfend

fitness = +precision = -generalization = +simplicity = +

Model 4: Complex and overfitting

PAGE 17

acdeh

abdeg

adceh

abdeh

acdeg

adceg

adbeh

acdefdbeh

adbeg

acdefbdeh

acdefbdeg

acdefdbeg

adcefcdeh

adcefdbeh

adcefbdeg

acdefbdefdbeg

adcefdbeg

adcefbdefbdeg

adcefdbefbdeh

adbefbdefdbeg

adcefdbefcdefdbeg

455

191

177

144

111

82

56

47

38

33

14

11

9

8

5

3

2

2

1

1

1

# trace

1391

astart register

request

cexamine casually

dcheckticket

decide reject request

e hend

aregister request

dexamine casually

ccheckticket

decide reject request

e h

a cexamine casually

dcheckticket

decide

e g

a dexamine casually

ccheckticket

decide

e g

register request

register request

pay compensation

pay compensation

aregister request

b dcheckticket

decide reject request

e h

aregister request

d bcheckticket

decide reject request

e h

a b dcheckticket

decide

e gregister request

pay compensation

examine thoroughly

examine thoroughly

examine thoroughly

… (all 21 variants seen in the log)

fitness = +, precision = +, generalization = -, simplicity = -

Overview

PAGE 18

process discovery

fitness

precisiongeneralization

simplicity

“able to replay event log” “Occam’s razor”

“not overfitting the log” “not underfitting the log”

astart register

request

bexamine

thoroughly

cexamine casually

dcheck ticket

decide

pay compensation

reject request

reinitiate request

e

g

h

f

end

astart register

request

cexamine casually

dcheckticket

decide reject request

e hend

astart register

request

bexamine thoroughly

cexamine casually

d checkticket

decide

pay compensation

reject request

reinitiate requeste

g

hfend

astart register

request

cexamine casually

dcheckticket

decide reject request

e hend

aregister request

dexamine casually

ccheckticket

decide reject request

e h

a cexamine casually

dcheckticket

decide

e g

a dexamine casually

ccheckticket

decide

e g

register request

register request

pay compensation

pay compensation

aregister request

b dcheckticket

decide reject request

e h

aregister request

d bcheckticket

decide reject request

e h

a b dcheckticket

decide

e gregister request

pay compensation

examine thoroughly

examine thoroughly

examine thoroughly

… (all 21 variants seen in the log)

astart register

request

bexamine

thoroughly

cexamine casually

dcheck ticket

decide

pay compensation

reject request

reinitiate request

e

g

h

f

end

astart register

request

cexamine casually

dcheckticket

decide reject request

e hend

astart register

request

bexamine thoroughly

cexamine casually

d checkticket

decide

pay compensation

reject request

reinitiate requeste

g

hfend

astart register

request

cexamine casually

dcheckticket

decide reject request

e hend

aregister request

dexamine casually

ccheckticket

decide reject request

e h

a cexamine casually

dcheckticket

decide

e g

a dexamine casually

ccheckticket

decide

e g

register request

register request

pay compensation

pay compensation

aregister request

b dcheckticket

decide reject request

e h

aregister request

d bcheckticket

decide reject request

e h

a b dcheckticket

decide

e gregister request

pay compensation

examine thoroughly

examine thoroughly

examine thoroughly

… (all 21 variants seen in the log)

astart register

request

bexamine

thoroughly

cexamine casually

dcheck ticket

decide

pay compensation

reject request

reinitiate request

e

g

h

f

end

astart register

request

cexamine casually

dcheckticket

decide reject request

e hend

astart register

request

bexamine thoroughly

cexamine casually

d checkticket

decide

pay compensation

reject request

reinitiate requeste

g

hfend

astart register

request

cexamine casually

dcheckticket

decide reject request

e hend

aregister request

dexamine casually

ccheckticket

decide reject request

e h

a cexamine casually

dcheckticket

decide

e g

a dexamine casually

ccheckticket

decide

e g

register request

register request

pay compensation

pay compensation

aregister request

b dcheckticket

decide reject request

e h

aregister request

d bcheckticket

decide reject request

e h

a b dcheckticket

decide

e gregister request

pay compensation

examine thoroughly

examine thoroughly

examine thoroughly

… (all 21 variants seen in the log)

astart register

request

bexamine

thoroughly

cexamine casually

dcheck ticket

decide

pay compensation

reject request

reinitiate request

e

g

h

f

end

astart register

request

cexamine casually

dcheckticket

decide reject request

e hend

astart register

request

bexamine thoroughly

cexamine casually

d checkticket

decide

pay compensation

reject request

reinitiate requeste

g

hfend

astart register

request

cexamine casually

dcheckticket

decide reject request

e hend

aregister request

dexamine casually

ccheckticket

decide reject request

e h

a cexamine casually

dcheckticket

decide

e g

a dexamine casually

ccheckticket

decide

e g

register request

register request

pay compensation

pay compensation

aregister request

b dcheckticket

decide reject request

e h

aregister request

d bcheckticket

decide reject request

e h

a b dcheckticket

decide

e gregister request

pay compensation

examine thoroughly

examine thoroughly

examine thoroughly

… (all 21 variants seen in the log)

PAGE 19

WMO process Harderwijk

PAGE 20

Process model discovered by HM10 Proces registratie

(start)530

10 Proces registratie(complete)

530

0,991530

20 Rapportage & beschikking(start)532

0,998530

20 Rapportage & beschikking(complete)

532

0,987532

0,998

Conformance checking of discovered model

PAGE 22

Performance Analysis

PAGE 23

Rijkswaterstaat

PAGE 24

PAGE 25

Catharina hospital (Eindhoven)

PAGE 26

2765 patients, 114,592 events, 619 different activities (taking event types into account) executed by 266 different individuals (doctors, nurses, etc.)

Fragment of process (2.9%)

18 activities of the 619 activities

PAGE 27

AMC hospital Amsterdam

PAGE 28

627 gynecological oncology patients, 24331 events, 376 different activities

ASML testing process

PAGE 29

Conclusion

PAGE 30

Petri’s guiding principles:1) Concurrency as a

starting point rather than an afterthought (locality of actions).

2) Formalism should be consistent with the laws of physics.

• We can observe processes; they leave footprints in event logs that can be extracted from various data sources.

• We can learn process models.• We can quantify the conformance of process

models (standard equivalence notions are useless).

• Ignoring this source of information is like studying physics while ignoring experimental results.

• Evidence-based Business Process Management!

PAGE 31

Process mining

PAGE 32

More Information

PAGE 33PAGE 33

IEEE Task Force on Process Mining

• ProM Software: prom.sourceforge.net• Process mining: www.processmining.org• ProM 5 series nightly builds: prom.win.tue.nl/tools/prom/nightly5/• ProM 6 series nightly builds: prom.win.tue.nl/tools/prom/nightly/• Converting logs (MXML-based) promimport.sourceforge.net • XES: www.xes-standard.org and www.openxes.org• Papers et al.: vdaalst.com• IEEE Task Force on Process Mining: www.win.tue.nl/ieeetfpm/