Outlier Detection - Data Mining: Concepts and Techniques - page 546

whether or not today's temperature value is an outlier depends on the context—the date,
the location, and possibly some other factors.
In a given data set, a data object is a contextual outlier if it deviates significantly
with respect to a specific context of the object. Contextual outliers are also known as
conditionaloutliers because they are conditional on the selected context. Therefore, in
contextual outlier detection, the context has to be specified as part of the problem defi-
nition. Generally, in contextual outlier detection, the attributes of the data objects in
question are divided into two groups:
Contextual attributes : The contextual attributes of a data object define the object's
context. In the temperature example, the contextual attributes may be date and
location.
Behavioral attributes : These define the object's characteristics, and are used to eval-
uate whether the object is an outlier in the context to which it belongs. In the
temperature example, the behavioral attributes may be the temperature, humidity,
and pressure.
Unlike global outlier detection, in contextual outlier detection, whether a data object
is an outlier depends on not only the behavioral attributes but also the contextual
attributes. A configuration of behavioral attribute values may be considered an outlier in
one context (e.g., 28 C is an outlier for a Toronto winter), but not an outlier in another
context (e.g., 28 C is not an outlier for a Toronto summer).
Contextual outliers are a generalization of local outliers, a notion introduced in
density-based outlier analysis approaches. An object in a data set is a local outlier if
its density significantly deviates from the local area in which it occurs. We will discuss
local outlier analysis in greater detail in Section 12.4.3.
Global outlier detection can be regarded as a special case of contextual outlier detec-
tion where the set of contextual attributes is empty. In other words, global outlier
detection uses the whole data set as the context. Contextual outlier analysis provides
flexibility to users in that one can examine outliers in different contexts, which can be
highly desirable in many applications.
Example 12.3 Contextual outliers. In credit card fraud detection, in addition to global outliers, an
analyst may consider outliers in different contexts. Consider customers who use more
than 90% of their credit limit. If one such customer is viewed as belonging to a group of
customers with low credit limits, then such behavior may not be considered an outlier.
However, similar behavior of customers from a high-income group may be considered
outliers if their balance often exceeds their credit limit. Such outliers may lead to busi-
ness opportunities—raising credit limits for such customers can bring in new revenue.