Chapter 5 Business Intelligence: Data Warehousing, Data

Download Report

Transcript Chapter 5 Business Intelligence: Data Warehousing, Data

DASHBOARDS
Dashboard provides the managers with
exactly the information they need in the
correct format at the correct time. BI
systems are the foundation of
dashboard, dashboards and scorecards
measure and display what is important.
It provide a real time view of data.
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-43
Dashboards / Brio
performance suite’s
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-44
Dashboards
BI Dashboards have spread to various nonfinancial
departments of firms, including sales and customer
service.
The table below give an example of how dashboard
have spread through organizations.
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-45
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-46
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-47
Business Intelligence and Analytics
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-48
OLAP
• Activities performed by end users in online systems
– Specific, open-ended query generation
• SQL
– Ad hoc reports
– Statistical analysis
– Building DSS applications
• Modeling and visualization capabilities
• Special class of tools // using SQL is helpful but not
sufficient for OLAP here a special class of tools is used, known
as :– DSS/BI/BA front ends
– Data access front ends
– Database front ends
– Visual information access systems
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-49
OLAP
The rules to evaluate OLAP on are : 1. Accessibility.
2. Transparency.
3. Multimedia conceptual view.
4. Consistence reporting performance.
5. Client – server architecture.
6. Generic dimensionality.
7. Multi- user support.
8. Flexible reporting.
9. Intuitive data manipulation.
10. Unlimited dimension & aggregation level.
11. Unrestricted cross dimensional operation.
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-50
Data Mining
Hollywood data mining case study. P.191
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-51
Data Mining
• Organizes and employs information and
knowledge from databases
• Statistical, mathematical, artificial
intelligence, and machine-learning
techniques
• Automatic and fast
• Tools look for patterns
– Simple models
– Intermediate models
– Complex Models
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-52
How data mining works
Data mining discovers information within data warehouses that
queries and reports can’t effectively reveal. Data mining tools
find pattern in data, there are 3 types of methods to identify
patterns in data:• Simple models (SQL- based query, OLAP, human judgment)
• Intermediate models (regression, decision tree, clustering)
• Complex models (neural network)
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-53
Data Mining
Data mining solving these classes of problems
–
–
–
–
Classification
Clustering
Association
Sequencing // like association but over a period of
time.
– Regression // form of estimation.
– Forecasting
– Others
• Hypothesis (we assume a situation & start investigation)or
discovery driven (it come from the facts).
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-54
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-55
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-56
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-57
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-58
Tools and Techniques
• Data mining techniques
– Statistical methods
– Decision trees // by dividing the problem into subproblems.
–
–
–
–
Case based reasoning // using historical cases.
Neural computing
Intelligent agents
Genetic algorithms
• Text Mining
– Hidden content // like document properties.
– Group by themes // by the common complaints
– Determine relationships // look for hidden unnoticed
that shows differences.
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-59
Summary :
Knowledge Discovery in Databases
• Data mining used to find patterns in
data
– Identification of data
– Preprocessing
– Transformation to common format
– Data mining through algorithms
– Evaluation
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-60
Data Visualization
• Technologies supporting visualization
and interpretation
– Digital imaging, GIS, GUI, tables,
multidimensions, graphs, VR, 3D,
animation
– Identify relationships and trends
• Data manipulation allows real time
look at performance data
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-61
Multidimensionality
• Data organized according to business
standards, not analysts
• Conceptualization business model
• Factors
– Dimensions: products, salespeople, business unit..
– Measures: money, sales volume, head count..
– Time: daily, weekly, ..
• Significant overhead and storage
• Expensive
• Complex
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-62
Analytic systems
• Real-time queries and analysis
• Real-time decision-making
• Real-time data warehouses updated
daily or more frequently
– Updates may be made while queries are
active
– Not all data updated continuously
• Deployment of business analytic
applications
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-63
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, 7th Edition,
Turban, Aronson, and Liang
5-64
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-65
Web Analytics/Intelligence
• Web analytics
– Application of business analytics to Web
sites
• Web intelligence
– Application of business intelligence
techniques to Web sites
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-66
Questions
1. Explain the issue of data quality and some of the measures one can
take to improve it.
2. Why OODBMS are the best solution to DSS.
3. What is data warehouse, and what are its benefits? Why is web
accessibility important?
4. Describe the major dimension of data quality.
5. Discuss what an organization should consider before making a
decision to purchase data- mining software.
6. Explain the process of text mining.
7. State the business intelligence assessment.
8. What is critical challenges for business intelligence success.
9. State the data warehouse risks
10. What is the characteristics of data warehousing?
11. What is the main database structures?
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-67
End of chapter 5
© 2005 Prentice Hall, Decision Support Systems and Intelligent Systems, 7th Edition,
Turban, Aronson, and Liang
5-68