Intelligent Data Warehousing from data preparation to data mining

1
Intelligent Data Warehousing from data
preparation to data mining

• Zhengxin Chen
• CRC Express

2
Goals

• To introduce the concepts, methods, and
  techniques of data warehousing and to give
  guidelines of planning, building, working,  and
  managing data warehouses.
• Outline
• Introduction
• Enterprise intelligence and artificial
  intelligence
• From DBMS to data warehousing
• Data preparation and preprocessing
• Building data warehouses
• Basics of materialized views
• Advanced in materialized views
• Intelligent data analysis
• Toward integrated OLAP and data mining

3
Chapter 1 Introduction

• 1.1 Why this book is needed
• 1.2 Features of the book
• 1.3 Why intelligent data warehousing
• 1.4 Organization of the book
• 1.5 How to use this book

4
1.1 Why this book is needed

• Decision support systems (DSSs) are rapidly
  becoming a key to gaining competitive advantage
  for business.
• Many corporations have built or are building
  unified decision-support databases, referred to
  as data warehouses, on which intelligent data
  analysis can be carried out.
• This book integrates theoretical and practical
  studies related to data warehousing from both
  computer science and MIS perspectives.
• It tries to bridge the gap between theoretical
  research and business applications.

5
Data warehouse definition

• By W.H. InmonA data warehouse is a
  subject-oriented, integrated, time-variant,
  nonvolatile collection of data in support of
  management decisions

6
Interesting issues in DW

• Business-driven vs. database and AI technologies
• DW stages how to prepare data, how to store data
  in DW, how to analyze data stored in DW using
  data mining techniques, and how to manage DWs.
• Research topics integration of data (with
  knowledge), integration of various methods
  applied on the data for analysis, warehouse
  design optimization (e.g. parts and whole), and
  metadata issues.

7
1.2 Features of the book

• State-of-the-art DW research and practice from an
  integrated business and computer science
  perspective.
• Intelligent data analysis techniques (i.e., data
  mining) in the context of DW.
• Existing literature and original research results
  with examples and case studies
• Intelligent techniques are applied to the entire
  process of DW
• A road map for studying intelligent data
  warehousing
• Text for general information and references for
  more technical details

8
1.3 Why intelligent data warehousing

• DW integrates data from multiple sources and
  provides different ways of looking at the data
  than do the databases being integrated Gupta
  and Mumick, 1998
• DW extends traditional interests of DBMS. The
  success or failure of DW is closely related to
  the historical development of DBMSs. DW has
  raised many challenging issues for the database
  community.
• There are various aspects of intelligence related
  to data warehousing, such as

9
AI/BI techniques

• Issues on the manipulation of huge amounts of
  data, the meaning of such data, the implication
  of these data, and the methodology used to
  analyze them.
• Building DW is an intelligent process, such as
  deciding what kind of data to be included
  (heuristic search, learning, and computational
  methods), Web-enabling techniques, and modeling
  user behavior for warehouse design.
• OLAP for decision support queries.
• Integration of OLAP and data mining.
• Science and engineering data warehousing
  applications.

10
1.4 Organization of the book

• Part I overview CH1 emphasizes on integrated
  data and an integrated methodology rooted in AI.
  CH2 discusses AI/BI from a business-oriented
  perspective. CH3 covers DW and DBMS, OLAP, and
  materialized views.
• Part II core materials on DW CH4 is on data
  preparation and preprocessing with a look at the
  overall DW lifecycle. CH5 examines DW building
  while CH67 are devoted to materialized views.
• Part III data analysis and knowledge discovery
  CH8 is on data mining (rough set, clustering,
  classification and association) and CH9 covers
  influential association rule mining which
  combines association rule mining and OLAP.

11
1.5 How to use this book

• This book assumes that readers have basic
  knowledge about DBMS.
• Two other companion book on decision support and
  data mining.
• References
• DBMS Silberschatz et al., 2001 Elmasri and
  Navathe, 2000
• DW/MIS Kimball et al. 1998 Kimball and Merz,
  2000
• DW/CS www-db.stanford.edu www.kdnuggets.com
• Data mining Han and Kamber 2000 Fayyad et al.,
  1996 Cios et al., 1998 Witten and Frank, 1999.