Slides supporting the book "Process Mining: Discovery, Conformance, and Enhancement of Business Processes" by Wil van der Aalst. See also http://springer.com/978-3-642-19344-6 (ISBN 978-3-642-19344-6) and the website http://www.processmining.org/book/start providing sample logs.
2. Overview
Chapter 1
Introduction
Part I: Preliminaries
Chapter 2 Chapter 3
Process Modeling and Data Mining
Analysis
Part II: From Event Logs to Process Models
Chapter 4 Chapter 5 Chapter 6
Getting the Data Process Discovery: An Advanced Process
Introduction Discovery Techniques
Part III: Beyond Process Discovery
Chapter 7 Chapter 8 Chapter 9
Conformance Mining Additional Operational Support
Checking Perspectives
Part IV: Putting Process Mining to Work
Chapter 10 Chapter 11 Chapter 12
Tool Support Analyzing “Lasagna Analyzing “Spaghetti
Processes” Processes”
Part V: Reflection
Chapter 13 Chapter 14
Cartography and Epilogue
Navigation
PAGE 1
3. Process discovery
supports/
“world” business
controls
processes software
people machines system
components
organizations records
events, e.g.,
messages,
specifies transactions,
models
configures etc.
analyzes
implements
analyzes
discovery
(process) event
conformance
model logs
enhancement
PAGE 2
4. Challenge
“able to replay event log” “Occam’s razor”
fitness simplicity
process
discovery
generalization precision
“not overfitting the log” “not underfitting the log”
PAGE 3
5. Observing a stable process infinitely long
frequent all behavior
behavior trace in (including noise)
event log
PAGE 4
10. Characteristics of process discovery
algorithms
• Representational bias
− Inability to represent concurrency
− Inability to deal with (arbitrary) loops
− Inability to represent silent actions
− Inability to represent duplicate actions
− Inability to model OR-splits/joins
− Inability to represent non-free-choice behavior
− Inability to represent hierarchy
• Ability to deal with noise
• Completeness notion assumed
• Approach used (direct algorithmic approaches, two-
phase approaches, computational intelligence
approaches, partial approaches, etc.) PAGE 9
11. Examples
• Algorithmic techniques
• Alpha miner
• Alpha+, Alpha++, Alpha#
• FSM miner
• Fuzzy miner
• Heuristic miner
• Multi phase miner
• Genetic process mining
• Single/duplicate tasks
• Distributed GM
• Region-based process mining
• State-based regions
• Language based regions
• Classical approaches not dealing with concurrency
• Inductive inference (Mark Gold, Dana Angluin et al.)
• Sequence mining
PAGE 10
12. Heuristic mining
• To deal with noise and incompleteness.
• To have a better representational bias than the α
algorithm (AND/XOR/OR/skip).
• Uses C-nets.
b
check
policy
a c e
register check close
claim damage case
d
consult
expert
PAGE 11
17. Lower threshold (2 direct successions and
a dependency of at least 0.7)
5(0.83)
b
11(0.92) 11(0.92)
a c e
11(0.92) 11(0.92)
13(0.93) 13(0.93)
d
4(0.80)
PAGE 16
18. Higher threshold (5 direct successions
and a dependency of at least 0.9)
b
11(0.92) 11(0.92)
a c e
11(0.92) 11(0.92)
13(0.93) 13(0.93)
d
PAGE 17
19. Learning splits and joins
5
20 b 20
21
5 20 20 5
20 20 20 20
a c e
40 20 21 20 40
13
13
13 13
13 13
d
4 17
4
4
PAGE 18
20. Alternative visualization
5
20 b 20
21
5 20 20 5
20 20 20 20
a c e
40 20 21 20 40
13
13
13 13
13 13
d b
4 17
4
4
AND AND
a c e
d
PAGE 19
21. Characteristics of heuristic mining
• Can deal with noise and therefore quite robust.
• Improved representational bias.
• Split and join rules are only considered locally
(therefore most of the discovered model are not
sound and require repair actions).
PAGE 20
22. Genetic process mining
create initial
population
event log mutation
next generation
compute
fitness
elitism
termination
tournament children
crossover
select best parents
individual
“dead” individuals
PAGE 21
23. Design decisions
• Representation of individuals
• Initialization
• Fitness function
• Selection strategy (tournament and elitism)
• Crossover create initial
population
• Mutation event log mutation
next generation
compute
fitness
elitism
termination
tournament children
crossover
select best parents
individual
“dead” individuals
PAGE 22
24. Example: crossover
b b
examine examine
thoroughly thoroughly
g g
pay pay
c c
compensation compensation
a e a e
examine examine
start register casually decide end start register casually decide end
request request
h h
d d
reject reject
check ticket request check ticket request
f f
reinitiate reinitiate
request request
b b
examine examine
thoroughly thoroughly
g g
pay pay
c c
compensation compensation
a e a e
examine examine
start register casually decide end start register casually decide end
request request
h h
d d
reject reject
check ticket request check ticket request
f f
reinitiate
reinitiate
request
request
PAGE 23
25. Example: mutation
remove place
b b
examine examine
thoroughly thoroughly
g g
pay pay
c c
compensation compensation
a e a e
examine examine
start register casually decide end start register casually decide end
request request
h h
d d
reject reject
check ticket request check ticket request
f f
reinitiate reinitiate
request
added arc request
PAGE 24
26. Characteristics of genetic
process mining
• Requires a lot of computing power.
• Can be distributed easily.
• Can deal with noise, infrequent behavior, duplicate tasks,
invisible tasks, etc.
• Allows for incremental improvement and combinations
with other approaches (heuristics post-optimization, etc.).
PAGE 25
27. Region-based mining
• Two types of regions theory:
− State-based regions
− Language-based regions
• All about discovering places (like in the α algorithm)!
a1 b1
a2 b2
... p(A,B) ...
am bn
A={a1,a2, … am} B={b1,b2, … bn}
PAGE 26
28. State-based regions
Two steps:
1.Discover a transition system (different abstractions
are possible)
2.Convert transition system into an “equivalent” Petri
net.
PAGE 27
29. Step 1: learning a transition system
current state
trace: abcdcdcde faghhhi
past future
past and future
• past, future, past+future
• sequence, multiset, set abstraction
• limited horizon to abstract further
• filtering e.g. based on transaction type, names, etc.
• labels based on activity name or other features
PAGE 28
30. Past without abstraction (full sequence)
c d
‹a,b›
‹a,b,c› ‹a,b,c,d›
b
a e d
‹› ‹a› ‹a,e› ‹a,e,d›
c
b d
‹a,c›
‹a,c,b› ‹a,c,b,d›
PAGE 29
31. Future without abstraction
a b ‹c,d›
‹a,b,c,d› ‹b,c,d› c
a e d
‹a,e,d› ‹e,d› ‹d › ‹›
b
a c
‹b,d›
‹a,c,b,d› ‹c,b,d›
PAGE 30
32. Past with multiset abstraction
[a,e]
d
[a,d,e]
e [a,b]
a b
[] [a]
c c
b d
[a,c] [a,b,c] [a,b,c,d]
PAGE 31
33. Only last event matters for state
‹e›
e d
a b
‹ b› d
‹› ‹a › c b ‹d›
c d
‹c›
PAGE 32
34. Step 2: constructing a Petri net using
regions
a = enter
b d b = enter
a e c = exit
d = exit
f d e = do not cross
e f = do not cross
e
f c
a
R
a c
e f
pR
b d
PAGE 33
35. Example
d
e
[a,e] [a,d,e]
[ a,b]
a b
[] [a] c
c
b d
[a,c] [a,b,c] [a,b,c,d]
b
a p1 e p3 d
start end
p2 c p4
PAGE 34
36. Language based regions
f c1
a1 b1
e c d
pR
a2 b2
X Y
Region R = (X,Y,c) corresponding to place pR: X = {a1,a2,c1} =
transitions producing a token for pR, Y = {b1,b2,c1} = transitions
consuming a token from pR, and c is the initial marking of pR. PAGE 35
37. Based idea: enough tokens should be
present when consuming
A place is feasible if it
can be added without
f c1 disabling any of the
traces in the event log.
a1 b1
e c d
pR
a2 b2
X Y
PAGE 36
41. Characteristics of region-based mining
• Can be used to discover more complex control-flow
structures.
• Classical approaches need to be adapted
(overfitting!).
• Representational bias can be parameterized (e.g.,
free-choice nets, label splitting, etc.).
• Problems dealing with noise.
PAGE 40
43. Evaluating the discovered process
Fitness: Is the event log
possible according to the
model?
Precision: Is the model Generalization: Is the model
not underfitting (allow for not overfitting (only allow for
too much)? the “accidental” examples)?
Structure: Is this the
simplest model (Occam's
Razor)?
PAGE 42