e signicance of knowledge discovery and data mining (KDDM) is on the rise
because it serves as the glue to supporting the successful deployment of organi-
zational learning for improved decision making and competitiveness. e aim
of this book Knowledge Discovery Process and Methods to Enhance Organizational
Performance is to provide some meaning or signicance to organizations and per-
sons who may be less experienced in the application of KDDM activities.
Although the terms “data mining” and “KDDM” are sometimes used inter-
changeably, data mining is but one step in a series of steps in the KDDM process.
Data mining is the process of extracting useful, relevant knowledge from any data
repository, big or small, whereas the KDDM process is the coordinated multistep
process of determining and delivering the business objectives by understanding the
business and data, mining the data to identify interesting and previously unknown
patterns. KDDM is generally viewed as an interdisciplinary eld that intersects arti-
cial intelligence, machine learning, statistics, and data mining; however, in the con-
text of organizational implementation, this is further augmented by an intersection
of project management; strategy; nancial management; and other business, legal,
privacy, ethical, and security considerations. Considerations of all these elements
underline its dynamism and are necessary for maximizing of the benets of KDDM
e current landscape presents an opportunity to present multiple conversa-
tions on the strategies to enhance the eectiveness of KDDM implementations
in organizations through discussion of diverse topics in the domain. is book
consists of 17 chapters with wide coverage relating to strategies, models, and tech-
niques relevant to the dierent stages of the KDDM process, including the business
understanding, data understanding, modeling (or data mining), deployment, and
evaluation stages; the application of dierent techniques to discover patterns; and
presentation of the importance and critical success factors in managing KDDM
initiatives, which are organized as follows:
Section I begins with an overall introduction to the current state of discus-
sions in KDDM followed by an introduction to the concept of KDDM and
the presentation of various models or perspectives adopted in academia and
industry to deliver data mining projects. An alternative model that attempts
to address some of the shortcomings in previous approaches is also presented.
Section II covers the development and application to techniques to help
improve the eciency and outcome of the phases of the KDDM. is
includes a discussion of a technique for the formulation of clearer business
objectives to better inform the direction of the project, the explication of the
activities in the business understanding phase to illustrate the importance of
a structured approach to completing core activities at the beginning of the
project, and the presentation of a semiautomated evaluation approach to pro-
mote the ecacy of the evaluation phase.
Section III commences with a conversation underlining the important role
of data mining to the sustainability of businesses, followed by insights into
the impact of poor-quality data on the successful implementation of these
types of projects and concludes with a formulation of critical success factors
in KDDM projects.
Section IV considers the advantages of discovering new knowledge through
the application of KDDM in multiple business situations. A survey of mul-
tiple applications of data mining in industries common in developing states
is presented to underline the vast opportunities that exist for the adoption
and use of KDDM. e use of multiple techniques, including cluster analysis
and neural networks, to determine the source of relative heterogeneity for an
investigator is proposed. e applications of data mining in organizational
behavior domain to understand project managers’ decision styles and second-
ary high school students’ performance are also presented.
Section V, the nal section, puts forward alternative methods for deriving
greater utility from data mining algorithms. A multiobjective analysis of post-
pruning phase to identify sub-tree, an integrated ensemble generation proce-
dure for selecting classiers and the formulation of a rank aggregation structure.
e book is intended for anyone with an interest in data mining and KDDM pro-
cesses. is pool includes practitioners; academic researchers, including experi-
enced researchers; and graduate and undergraduate students engaged in KDDM
activities, particularly in the less developed and emerging countries. e conversa-
tions relating to dierent methods, techniques, and application of KDDM activi-
ties will be of particular interest to persons and organizations that are relatively less
experienced in conducting KDDM initiatives. It will also showcase how to design
and implement these initiatives.

Get Knowledge Discovery Process and Methods to Enhance Organizational Performance now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.