Deck 11: Automated Decision Systems and Expert Systems

Question 1

Most business decision rules are the same across industries.

Answer 1

False

Question 2

A revenue management (RM) system for an airline seeks to minimize each customer's ticket price of travel on the airline's flights.

Answer 2

False

Question 3

While most first-generation Expert Systems (ES) use if-then rules to represent and store their knowledge, second-generation ES are more flexible in adopting multiple knowledge representation and reasoning methods.

Answer 3

True

Question 4

Rules used in automated decision systems (ADS) can be derived based on experience.

Question 5

Inference rules and knowledge rules are both used to solve problems in a rule-based expert system.

Question 6

Once validated, the knowledge acquired from experts or induced from a set of data must be represented in a format that does not need to be understandable by humans but must be executable on computers.

Question 7

A nonexpert uses the development environment of an expert system to obtain advice and to solve problems using the expert knowledge embedded into the system.

Question 8

Expert systems (ES) are computer-based information systems that use expert knowledge to attain high-level decision performance in a narrowly defined problem domain.

Question 9

The knowledge base in an expert system must correspond exactly to the format of the knowledge base in the organization where it will be utilized.

Question 10

The inference engine, also known as the control structure or the rule interpreter (in rule-based ES), is essentially a computer program that provides a methodology for reasoning about information in the knowledge base and on the blackboard to formulate appropriate conclusions.

Question 11

Knowledge acquisition from experts is a complex task that requires specialized expertise to conduct successfully.

Question 12

The critical component of a knowledge refinement system is the self-learning mechanism that allows it to adjust its knowledge base and its processing of knowledge based on the evaluation of its recent past performances.

Question 13

Validation of knowledge is usually done by a human expert in the knowledge domain.

Question 14

Rich and Knight (1991) defined artificial intelligence as "the study of how to make people do things at which, at the moment, computers are better."

Question 15

Unlike human experts, expert systems do not need to explain their views, recommendations, or decisions.

Question 16

Rule-based systems have their roots in artificial intelligence.

Question 17

Flight pricing systems are examples of semi-automated decision systems that require managerial input for each decision.

Question 18

The basic rationale of artificial intelligence is to use mathematical calculation rather than symbolic reasoning.

Question 19

The case study on chemical, biological, and radiological agents shows that expert systems are widely used in high pressure situations where the human decision makers are confident in taking quick actions.

Question 20

A person's decision performance and level of knowledge are typical criteria that determine their level of expertise in a particular subject.

Question 21

In the sport talents identification case study, the expert system was calibrated with expertise from

A) multiple sports experts.
B) one overall sports expert.
C) ) the system developer.
D) subjects in the cases used to create the ES.

Question 22

Which module is missing from most expert systems?

A) user interface subsystem
B) knowledge base subsystem
C) inference engine
D) knowledge refinement subsystem

Question 23

Which of the following is NOT a stage of knowledge engineering?

A) knowledge consolidation
B) knowledge representation
C) knowledge acquisition
D) knowledge validation

Question 24

In the InterContinental Hotel Group case study, the mathematical model used to increase profits was based on

A) a simulation model that tried out many options.
B) a system that collated the subjective inputs of managers.
C) a mathematical model that used two variables: price and day of the week.
D) an optimization model that used multiple variables.

Question 25

Which tool would be best to use when there is a need to very rapidly and cheaply develop a rule-based expert system?

A) LISP or Prolog languages
B) ASP.NET
C) an ES shell
D) C++

Question 26

In the heart disease diagnosis case study, what was a benefit of the SIPMES expert system?

A) Expert systems from other domains were used, saving development time.
B) The SIPMES system agreed with human experts 64% of the time.
C) The SIPMES system could diagnose all types of cardiovascular diseases.
D) No human expert knowledge was needed in development, only textbook knowledge.

Question 27

Which category of expert systems that includes weather forecasting and economic/financial forecasting?

A) diagnostic ES
B) planning ES
C) instruction ES
D) prediction ES

Question 28

In the chemical, biological, and radiological agents case study, the CBR Advisor program had all the following features EXCEPT

A) it could provide advice even incomplete information.
B) it was tailored to different types of users.
C) it was available online to the general public.
D) it was created by multiple experts.

Question 29

How does an expert system differ from conventional systems?

A) Changes in an expert system are tedious to make.
B) The expert system operates only when it is complete.
C) Expert systems handle qualitative data easily.
D) Execution of expert system programs is algorithmic or step-by-step.

Question 30

Using certainty factors, a rule declares that IF competition is strong, CF = 70 AND margins are above 15% CF = 100 THEN sales demand will decline. If both conditions are true, what is the CF of the conclusion?

A) 100%
B) 70%
C) 30%
D) 21%

Question 31

It is difficult to acquire knowledge from experts for all the following reasons EXCEPT

A) experts may not be able to put into words how they conduct their work.
B) testing and refining of knowledge is complex and difficult.
C) many business areas have no identifiable experts.
D) experts often change their behavior when observed.

Question 32

The MYCIN Expert System was used to diagnose bacterial infections using

A) a simulation model that tried out many options.
B) a set of 500 rules on the subject.
C) an optimization model.
D) an expert system whose performance was inferior to human experts.

Question 33

What does self-knowledge in an expert system (ES) mean?

A) An ES understands itself in a very human sense.
B) An ES understands the human decision maker.
C) The ES can explain how it reached a conclusion.
D) The ES "knows" that it exists.

Question 34

Using certainty factors, a rule declares that IF competition is strong, CF = 70 OR margins are above 15% CF = 100 THEN sales demand will decline. If both conditions are true, what is the CF of the conclusion?

A) 100%
B) 70%
C) 30%
D) 21%

Question 35

In the Giant Food Stores case study, the new pricing model deployment system included all the following features EXCEPT

A) it required more staff to make pricing changes.
B) it could handle large numbers of price changes.
C) it used point of sale and competitive data as inputs.
D) it had a predictive capability.

Question 36

Who are automated decision systems (ADS) primarily designed for?

A) strategic level managers making long-term, wide-ranging decisions
B) mid-level managers making tactical decision
C) frontline workers who must make decisions rapidly
D) operational managers who make shop floor decisions

Question 37

All the following statements about how an expert system operates are true EXCEPT

A) incorporated knowledge is drawn exclusively from human experts.
B) a knowledge engineer creates inferencing rules.
C) knowledge rules are stored in the knowledge base.
D) inference engines contain an explanation subcomponent.

Question 38

What would explain why a divorce attorney in New York City may not be considered an expert in Beijing, China?

A) You need a greater level of experience in Beijing to practice law.
B) No criteria to evaluate divorce attorneys exist in Beijing.
C) The divorce attorney in New York does not speak Mandarin.
D) Expertise is frequently domain dependent.

Question 39

In the Clinical Decision Support System case study, what was the system's output?

A) a diagnosis of the type of tendon injury suffered by the patient
B) a treatment and rehabilitation plan for the patient
C) an explanation of the tendon anatomy of the patient
D) a referral to specialists who could accurately diagnose the tendon injury

Question 40

Revenue management systems modify the prices of products and services dynamically based on

A) intuition, demand, and supply.
B) intuition, competition, and supply.
C) business rules, demand, and supply.
D) business rules, supply, and intuition.

Question 41

Expert systems mimic the reasoning process of ________ experts in order to solve problems.

Question 42

The accumulation, transfer, and transformation of problem-solving expertise from experts or documented knowledge sources to a computer program for constructing or expanding the knowledge base is known as ________.

Question 43

________ is a collection of concepts and ideas that are related to the development of intelligent systems.

Question 44

________ is a collection of specialized facts, procedures, and judgment usually expressed as rules.

Question 45

The knowledge possessed by human experts is often lacking in ________ and not explicitly expressed.

Question 46

In the popular Corvid ES shell, ________ define the major factors considered in problem solving.

Question 47

Knowledge rules, or ________ rules, state all the facts and relationships about a problem.

Question 48

________ chaining is a data-driven approach in which we start from available information as it becomes available or from a basic idea, and then we try to draw conclusions.

Question 49

________ blocks in the Corvid ES determine(s) how the system interacts with the user, including the order of execution and the user interface.

Question 50

After an ES system is built, it must be evaluated in a two-step process. The first step, ________, ensures that the resulting knowledge base contains knowledge exactly the same as that acquired from the expert.

Question 51

Rules derived from data ________ can be used effectively in automated decision systems.

Question 52

After an ES system is built, it must be evaluated in a two-step process. The second step, ________, ensures that the system can solve the problem correctly.

Question 53

The ability of human experts to analyze their own knowledge and its effectiveness, learn from it, and improve on it for future consultations is known as a ________.

Question 54

An ________ shell is a type of development tool that has built-in inference capabilities and a user interface, and is specifically designed for ES development.

Question 55

An ________ infers situation descriptions from observations, and explains observed data by assigning them symbolic meanings that describe the situation.

Question 56

In the Corvid ES shell, ________ blocks are the decision rules acquired from experts.

Question 57

________ chaining is a goal-driven approach in which you start from an expectation of what is going to happen (i.e., hypothesis) and then seek evidence that supports (or contradicts) your expectation.

Question 58

________ (or reasoning) is the process of using the rules in the knowledge base along with the known facts to draw conclusions.

Question 59

________ express belief in an event (or a fact or a hypothesis) based on the expert's assessment.

Question 60

Inference rules, or ________ rules, offer advice on how to solve a problem, given that certain facts are known.

Question 61

Describe the Turing test for determining whether a computer exhibits intelligent behavior.

Question 62

List five applications of artificial intelligence.

Question 63

Name and describe three problem areas suitable for expert systems.

Question 64

A relatively new approach to supporting decision making is called automated decision systems (ADS), sometimes also known as decision automation systems (DAS). Give a definition of an ADS/DAS in simple terms?

Question 65

What is knowledge engineering?

Question 66

The development of expert systems is often described as a tedious process. What activities does it typically include?

Question 67

Describe, with examples, the two basic ideas most experts agree that artificial intelligence (AI) is concerned with.

Question 68

What are three components that may be included in an expert system in addition to the three major components found in virtually all expert systems?

Question 69

List five disciplines of artificial intelligence.

Question 70

What are the various components of an airline revenue management system? Describe the function of each one.