Page 261 -
P. 261
9.1 Refined Process Mining Framework 243
they refer to. Most event logs considered thus far contained only historic, i.e., “post
mortem”, event data. “Pre mortem” event data refer to cases that have not yet com-
pleted. If a case is still running, i.e., the case is still “alive” (pre mortem), then it
may be possible that information in the event log about this case (i.e., current data)
can be exploited to ensure the correct or efficient handling of this case.
“Post mortem” event data is most relevant for off-line process mining, e.g., dis-
covering the control-flow of a process based on one year of event data. For online
process mining, a mixture of “pre mortem” (current) and “post mortem” (historic)
data is needed. For example, historic information can be used to learn a predictive
model. Subsequently, information about a running case is combined with the pre-
dictive model to provide an estimate for the remaining flow time of the case.
The refined process mining framework also distinguishes between two types of
models: “de jure models” and “de facto models”. A de jure model is normative, i.e., it
specifies how things should be done or handled. For example, a process model used
to configure a BPM system is normative and forces people to work in a particular
way. A de facto model is descriptive and its goal is not to steer or control reality.
Instead, de facto models aim to capture reality. The techniques presented in Chaps. 5
and 6 aim to produce de facto models. Figure 9.1 also highlights that models can
cover different perspectives, i.e., process mining is not limited to control-flow and is
also concerned with resources, data, organizational entities, decision points, costs,
etc. The two large arrows in Fig. 9.1 illustrate that de facto models are derived from
reality (right downward arrow) and that de jure models aim to influence reality (left
upward arrow).
After refining event logs into “pre mortem” and “post mortem” and partitioning
models into “de jure” and “de facto”, we can identify ten process mining related
activities as shown in Fig. 9.1. These ten activities are grouped into three categories:
cartography, auditing, and navigation.
9.1.1 Cartography
Process models can be seen as the “maps” describing the operational processes of
organizations, i.e., just like geographic maps, process models aim to describe reality.
In order to do this, abstractions are needed. For example, on a roadmap a highway
may be denoted by an orange line having a thickness of four millimeters. In reality
the highway will not be orange; the orange coloring is just used to emphasize the
importance of highways. If the scale of the map is 1 : 500,000, then the thickness of
the line corresponds to a highway of 2 kilometers wide. In reality, the highway will
not be so broad. If the thickness of the line would correspond to reality (assuming
the same scale), it would be approximately 0.05 millimeter (for a highway of 25 me-
ters wide). Hence, the highway would be (close to) invisible. Therefore, the scale is
modified to make the map more readable and useful. When making process models,
we need to use similar abstractions. In Chap. 13, we will elaborate on the relation-
ships between process maps and geographic maps. Also note that in Sect. 5.4.4 we