Chapter 1 - Introduction
Intelligent & Knowledge Based Systems, Business Analytics
Lecture 1
Contents
1. Basic concepts
AI, smart systems, knowledge based systems
2. Business intelligence and corporate reporting
3. Knowledge engineering and management (Knowledge-based AI)
• Elements of knowledge based systems: knowledge
representation, inference and reasoning, dealing with
uncertainty, verification and validation
• Building knowledge based systems: knowledge acquisition, knowledge systems
development
• Organizational aspects
• Knowledge management
2. Knowledge discovery/Business Analytics (Data-based AI)
• Intro to analytics, predictive and descriptive data mining, supervised and
unsupervised learning
• RapidMiner toolset
Context
Chapter 1, 2, 4 & 5 1
,Decision making improvement
This course is about knowledge and intelligence
The DIKW hierarchy
§ How to build smart systems that use knowledge
§ How to organize knowledge
§ How to ensure knowledge quality
§ How to discover knowledge from data
§ How to get value out of it
§ How to make it actionable
§ How to manage knowledge
§ How to make decisions based on knowledge
Decision making => knowledge needed to support decision making.
Data has no meaning => numbers or words. When we give a meaning to data that we produce information.
Produce information to make better decisions. Data with a meaning.
With the information => still have to use the information to do something with it = knowledge. Leads to an
action/decision. Wisdom = what we as humans could know. Not automation.
Data, Information and Knowledge
• Information
relevant data made available on time and in the correct form. Management decisions can be taken,
based upon this information.
• Data
raw facts, numbers, documents. Data do not have an intrinsic value but receive it in a certain context
and for a specific audience.
• Knowledge
the way to deal with the information, to take decisions, to establish relations between data. This does
not refer to factual knowledge (knowledge about the facts), but knowledge to deal with the facts.
• “Organizations that spend millions capturing and protecting data in the most expensive
computer systems in the world,
... still keep their knowledge assets in three-ring binders” (A. Barr)
Data = only receives value in a certain context. Number = 2.5 => does not say anything.
Chapter 1, 2, 4 & 5 2
,Data handling. Organizing data. Should spend more money on what to do with the facts. Often in the head of
people, hidden ways of doing things… need to start organizing these things = decision making.
AI and Knowledge
Left: start from large amounts of data => derive knowledge.
Right: start from human knowledge & model & manage it. Corpus of knowledge.
Want to use this knowledge to make decisions => make sure that our decisions = well-supported & in some
cases: automate the whole cycle from knowledge building to applying the knowledge in a system and make
automatic decisions.
Course Objectives
• Upon completion of this course, the student is able to:
• understand the concepts of data warehousing and business intelligence in order to
provide integrated information according to business needs.
• acknowledge the importance of unstructured information and suggest recent
technologies to support that. recognize and formulate different knowledge
management strategies depending on company and product type.
• understand and compare different knowledge representation forms and reasoning
strategies.
• detect opportunities to discover knowledge from large amounts of data (knowledge
discovery).
• implement, run and evaluate data mining experiments using a specific toolset.
• evaluate and discuss the application of analytics in real life situations.
• The focus of the course is on information and knowledge management as opposed to c.q.
integrated with traditional information processing.
Chapter 1, 2, 4 & 5 3
, Information & knowledge management. Not info processing point of view but AI point of view.
Chapter 1, 2, 4 & 5 4
Intelligent & Knowledge Based Systems, Business Analytics
Lecture 1
Contents
1. Basic concepts
AI, smart systems, knowledge based systems
2. Business intelligence and corporate reporting
3. Knowledge engineering and management (Knowledge-based AI)
• Elements of knowledge based systems: knowledge
representation, inference and reasoning, dealing with
uncertainty, verification and validation
• Building knowledge based systems: knowledge acquisition, knowledge systems
development
• Organizational aspects
• Knowledge management
2. Knowledge discovery/Business Analytics (Data-based AI)
• Intro to analytics, predictive and descriptive data mining, supervised and
unsupervised learning
• RapidMiner toolset
Context
Chapter 1, 2, 4 & 5 1
,Decision making improvement
This course is about knowledge and intelligence
The DIKW hierarchy
§ How to build smart systems that use knowledge
§ How to organize knowledge
§ How to ensure knowledge quality
§ How to discover knowledge from data
§ How to get value out of it
§ How to make it actionable
§ How to manage knowledge
§ How to make decisions based on knowledge
Decision making => knowledge needed to support decision making.
Data has no meaning => numbers or words. When we give a meaning to data that we produce information.
Produce information to make better decisions. Data with a meaning.
With the information => still have to use the information to do something with it = knowledge. Leads to an
action/decision. Wisdom = what we as humans could know. Not automation.
Data, Information and Knowledge
• Information
relevant data made available on time and in the correct form. Management decisions can be taken,
based upon this information.
• Data
raw facts, numbers, documents. Data do not have an intrinsic value but receive it in a certain context
and for a specific audience.
• Knowledge
the way to deal with the information, to take decisions, to establish relations between data. This does
not refer to factual knowledge (knowledge about the facts), but knowledge to deal with the facts.
• “Organizations that spend millions capturing and protecting data in the most expensive
computer systems in the world,
... still keep their knowledge assets in three-ring binders” (A. Barr)
Data = only receives value in a certain context. Number = 2.5 => does not say anything.
Chapter 1, 2, 4 & 5 2
,Data handling. Organizing data. Should spend more money on what to do with the facts. Often in the head of
people, hidden ways of doing things… need to start organizing these things = decision making.
AI and Knowledge
Left: start from large amounts of data => derive knowledge.
Right: start from human knowledge & model & manage it. Corpus of knowledge.
Want to use this knowledge to make decisions => make sure that our decisions = well-supported & in some
cases: automate the whole cycle from knowledge building to applying the knowledge in a system and make
automatic decisions.
Course Objectives
• Upon completion of this course, the student is able to:
• understand the concepts of data warehousing and business intelligence in order to
provide integrated information according to business needs.
• acknowledge the importance of unstructured information and suggest recent
technologies to support that. recognize and formulate different knowledge
management strategies depending on company and product type.
• understand and compare different knowledge representation forms and reasoning
strategies.
• detect opportunities to discover knowledge from large amounts of data (knowledge
discovery).
• implement, run and evaluate data mining experiments using a specific toolset.
• evaluate and discuss the application of analytics in real life situations.
• The focus of the course is on information and knowledge management as opposed to c.q.
integrated with traditional information processing.
Chapter 1, 2, 4 & 5 3
, Information & knowledge management. Not info processing point of view but AI point of view.
Chapter 1, 2, 4 & 5 4
