Summary Decision Support Systems
Lecture 1
Decision support system: An umbrella term to describe any computerized system that
supports decisionmaking in an organization. It’s a set of expandable, interactive IT
techniques and tools designed for processing and analysing data and for supporting
managers in decision making. To do this, the system matches individual resources of
managers with computer resources to improve the quality of the decision made. It’s mainly
evolved from two research fields: decision making processes for organizations and technical
research on interactive IT systems.
Data : Items that are the most elementary description of things
- Structured data = What you find in a DB
- Unstructured data = What you find in the ‘wild’, like text and images
Information : Organized data that has meaning
Knowledge : Processed data or information that can help solve business problems
3 ways of Business Analytics
Descriptive Analytics: Use data to understand past and present
Predictive Analytics : Predict future behaviour
Prescriptive Analytics : Make recommendations to achieve max performance.
,Introduction to Business Intelligence
Business intelligence is an umbrella term that combines the processes , technologies and
tools needed to transform data into information.
Transform data -> information -> knowledge -> plans that drive profitable business action
Business intelligence is also known as Information and knowledge that enables business
decision-making.
BI Product : Provide a good insight about past present and future business operations.
- Understanding customer preferences
- Coping with competition
- Identifying growth opportunities
- Enhancing efficiency
Bi Tools and Techniques :
- Data warehousing
- Knowledge management
- Query and reporting
- Dashboards
- Statistics
- Data, process and text mining
Introduction to Data warehousing
Data warehouse : A subject-oriented, integrated, time variant and nonvolatile collection of
data which is maintained separately from the organisation’s operational databases for
managerial decision making.
Data warehousing : The process of constructing and using data warehouses.
, The data warehouse is separate because:
- Historic data , decision support requires historic data which is not stored in
operational DB;s
- Data integration and consolidation, data warehousing requires that data is
summarised from the same sources.
- Data quality , different sources have different data types and formats which have to
be reconciled for decision making
About data warehousing
- Subject oriented : Because the warehouse is for the analysis of data for decision
making and not for daily operations. It can exclude unimportant data
- Integrated : The warehouse is constructed by integration of multiple data sources.
Data cleaning and data integration techniques are applied to ensure consistency
- Time variant : In the warehouse the time horizon is significantly longer than that of
normal operational systems. It can go back 5-10 years. Everything is labelled on time
- Nonvolatile : Operational updates of data do not occur in the data warehouse.
ETL Staging area
- Extract data from other systems
- Transform data (cleaning etc)
- Load data into warehouse
- Temporary storage and very complex!
Data warehouse
- High quality data
- Data Hardly changes
- Consistent and historic data
Lecture 1
Decision support system: An umbrella term to describe any computerized system that
supports decisionmaking in an organization. It’s a set of expandable, interactive IT
techniques and tools designed for processing and analysing data and for supporting
managers in decision making. To do this, the system matches individual resources of
managers with computer resources to improve the quality of the decision made. It’s mainly
evolved from two research fields: decision making processes for organizations and technical
research on interactive IT systems.
Data : Items that are the most elementary description of things
- Structured data = What you find in a DB
- Unstructured data = What you find in the ‘wild’, like text and images
Information : Organized data that has meaning
Knowledge : Processed data or information that can help solve business problems
3 ways of Business Analytics
Descriptive Analytics: Use data to understand past and present
Predictive Analytics : Predict future behaviour
Prescriptive Analytics : Make recommendations to achieve max performance.
,Introduction to Business Intelligence
Business intelligence is an umbrella term that combines the processes , technologies and
tools needed to transform data into information.
Transform data -> information -> knowledge -> plans that drive profitable business action
Business intelligence is also known as Information and knowledge that enables business
decision-making.
BI Product : Provide a good insight about past present and future business operations.
- Understanding customer preferences
- Coping with competition
- Identifying growth opportunities
- Enhancing efficiency
Bi Tools and Techniques :
- Data warehousing
- Knowledge management
- Query and reporting
- Dashboards
- Statistics
- Data, process and text mining
Introduction to Data warehousing
Data warehouse : A subject-oriented, integrated, time variant and nonvolatile collection of
data which is maintained separately from the organisation’s operational databases for
managerial decision making.
Data warehousing : The process of constructing and using data warehouses.
, The data warehouse is separate because:
- Historic data , decision support requires historic data which is not stored in
operational DB;s
- Data integration and consolidation, data warehousing requires that data is
summarised from the same sources.
- Data quality , different sources have different data types and formats which have to
be reconciled for decision making
About data warehousing
- Subject oriented : Because the warehouse is for the analysis of data for decision
making and not for daily operations. It can exclude unimportant data
- Integrated : The warehouse is constructed by integration of multiple data sources.
Data cleaning and data integration techniques are applied to ensure consistency
- Time variant : In the warehouse the time horizon is significantly longer than that of
normal operational systems. It can go back 5-10 years. Everything is labelled on time
- Nonvolatile : Operational updates of data do not occur in the data warehouse.
ETL Staging area
- Extract data from other systems
- Transform data (cleaning etc)
- Load data into warehouse
- Temporary storage and very complex!
Data warehouse
- High quality data
- Data Hardly changes
- Consistent and historic data
