Chapter 5 Business Intelligence Data Warehousing Data Acquisition

Chapter 5: Business Intelligence: Data Warehousing, Data Acquisition, Data Mining, Business Analytics, and Visualization DECISION SUPPORT SYSTEMS AND BUSINESS INTELLIGENCE , Eighth Edition 1

Data, Information, Knowledge § Data § Items that are the most elementary descriptions of things, events, activities, and transactions § May be internal or external § Information § Organized data that has meaning and value § Knowledge § Processed data or information that conveys understanding or learning applicable to a problem or activity © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7 th Edition, Turban, Aronson, and Liang 5 -2

Business Intelligence and Analytics § Business intelligence § Acquisition of data and information for use in decision-making activities § Business analytics § It adds an additional dimension to BI : Models and solution methods § Data mining § Applying models and methods to data to identify patterns and trends © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7 th Edition, Turban, Aronson, and Liang 5 -3

Dash. Board § It provides managers with exactly the information they need in the correct format at the correct time. § Dashboard and scorecards measure display what is important. 4

Data Mining § Organizes and employs information and knowledge from databases § It uses statistical, mathematical, artificial intelligence, and machine-learning techniques § Automatic and fast by focusing attention on the most important variables. . § Data mining includes tasks known as knowledge extraction, data exploration, data pattern processing. © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7 th Edition, Turban, Aronson, and Liang 5 -5

How data mining works? § It discovery information within data warehouses that queries and reports cannot effectively reveal. § Data mining tools find patterns in data and infer rule from them. § These pattern and rule can be used to guide decision -making. § It is supported by set of algorithms approach to extract the relevant relationship in the data 6

Data Mining algorithms § § § § Classification Clustering Association Sequencing Regression Forecasting Others © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7 th Edition, Turban, Aronson, and Liang 5 -7

Data Mining algorithms (cont. ) § Classification : defining the characteristic of certain group. § Decision tree and neural network are useful techniques. § Clustering : identifies group of items that share a certain characteristics. § Clustering approach can be used to identify class of customers. 8

Data Mining algorithms (cont. ) § Association : identifies relationship between event that occur at one time. § Statistical method are typically used. § Sequencing: similar to association except that the relationship occurs over a period time. § Regression : used to map data to a prediction value. § Linear and nonlinear technique are used § Forecasting: estimate future value based on pattern within large set of data. § Other: it is based on advanced artificial intelligence 9 method.

Data Mining (cont. ) § Data mining can be either Hypothesis or discovery driven. § Hypothesis driven data mining begins with proposition by the user. § Discovery driven data mining finds pattern, associations and relationship among the data. § Data mining is iterative. 10

Tools and techniques § Data mining § § § Statistical methods Decision trees Case based reasoning Neural computing Intelligent agents Genetic algorithms © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7 th Edition, Turban, Aronson, and Liang 5 -11

Text Mining § It is the application of data mining to nonstructred or less structured text files. § Text mining help organization to § Find Hidden content § Group by themes § Determine relationships 12

Sampler of data mining application § Marketing : prediction which customer will respond to buy a particular product. § Banking: which kind of customers will best respond to new loan offers. § Manufacturing: predicting when to expect machinery failures. : : : 13

Knowledge Discovery in Databases § KDD define as process of using data mining method to find useful information and pattern in the data. © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7 th Edition, Turban, Aronson, and Liang 5 -14

KDD process § Selection : Identification of data § Preprocessing: missing data must be dealt with, involves correction and/or utilizing predicted values. § Transformation to common format § Data mining : applying through algorithms § Interpretation /Evaluation: data must be presented in manner that is meaningful to the users. 15

Data Visualization § Technologies supporting visualization and interpretation § Digital imaging, GIS, GUI, tables, multidimensions, graphs, VR, 3 D, animation § Identify relationships and trends § Data manipulation allows real time look at performance data © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7 th Edition, Turban, Aronson, and Liang 5 -16

GIS § Computerized system for managing and manipulating data with digitized maps § § Geographically oriented Geographic spreadsheet for models Software allows web access to maps Used for modeling and simulations © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7 th Edition, Turban, Aronson, and Liang 5 -17

© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7 th Edition, Turban, Aronson, and Liang 5 -18

Web Analytics/Intelligence § Web analytics § Term used to describes the application of business analytics to Web sites § Web intelligence § Term used to describes the application of business intelligence techniques to Web sites © 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7 th Edition, Turban, Aronson, and Liang 5 -19