Databases Reference
In-Depth Information
an action tree which can be used to construct extended action rules from the
leaf nodes of the same parent.
2 Goal of E-Action Rules
The aim of an e-action rule is to look at the actionability in an objective
way because e-action rules evaluate discovered classification rules based on
statistics and structures of patterns. E-action rule is data driven and domain
independent because it is based on the strategy which does not depend on
domain knowledge. We claim that actionability does not have to be seen
as a purely subjective concept. The definition of e-action rules is objective.
However, we can not omit some degree of subjectivity in determining the
attribute class and what action to take. In order to do that, we divide all
attributes into two parts, stable and flexible. Obviously, this classification
has to be done by users to decide which attributes are stable and which are
flexible. This is a purely subjective decision. A stable attribute has no influence
on reclassification, but a flexible attribute does influence changes. Users have
to be careful judging which attributes are stable and which are flexible. If we
apply e-action rules on objects then their flexible attributes can be changed
but the stable attributes remain the same. Basically, an e-action rule shows
that some selected objects can be reclassified from an undesired decision state
to a desired one by changing some of the values of their flexible features. How
to take an action on those flexible attributes can be determined by following
either objective or subjective approach. It depends on the characteristic of
the corresponding flexible attributes. If the attribute is an interest rate on
the bank account then the bank can take an action as the rule states (i.e.,
lower the interest rate to 4.75%). So, in this case, it is a purely objective
decision. However, if the attribute is a fever then doctors may chose several
alternative treatments for decreasing patient
s temperature. The choice of a
treatment is a subjective decision. Basically, we cannot eliminate some amount
of subjectivity in that process.
3 Information System and E-Action Rules
An information system is used for representing knowledge. Its definition, pre-
sented here, is due to Pawlak [7].
By an information system we mean a pair
S
=(
U,A
), where:
•
U
is a nonempty, finite set of objects
•
A
is a nonempty, finite set of attributes i.e.
a
:
U
−→
V
a
is a function for
any
a ∈ A
,where
V
a
is called the domain of
a
Elements of
U
are called objects. In this chapter, for the purpose of clarity,
objects are interpreted as customers. Attributes are interpreted as features
such as, offers made by a bank, characteristic conditions, etc.
