1. What is a decision? When does a person have to make a decision? A decision is a conclusion or resolution reached after a thought out consideration of variables in a problem. When more than one possible action is involved in solving a problem, a decision must be made. 2. Calculating a complex trajectory of a spaceship to Mars is a structured problem, whereas diagnosing the cause of a rash on a person’s skin is often unstructured. How so? A structured problem is one in which an optimal solution can be reached through a single set of steps. Since the one set of steps is known, and since the steps must be followed in a known sequence, solving a structured problem with the same data always yields the same solution. This sequence of steps is known as an algorithm. An unstructured problem is one for which there is no algorithm to follow to reach an optimal solution— either because there is not enough information about the factors that might affect the solution or because there are so many potential factors that no algorithm can be formulated to guarantee a unique optimal solution. Unstructuredness is closely related to uncertainty. 3. DSSs use models to process data. Explain what a model is. Give an example that is not mentioned in the chapter. A sequence of events or a pattern of behavior might become a useful model when the relationships among its inputs, outputs, and conditions can be established well enough that they can be used to analyze different parameters. Models are used to predict output on the basis of different input or different conditions or to estimate what combination of conditions and input might lead to a desired output. Models are often based on mathematical research or on experience. A model might be a widely used method to predict performance, such as best- fit linear analysis, or it might be built by the organization, using the experience that employees in the firm have accumulated over time. 4. Many DSSs are not stand- alone anymore, but are embedded in other ISs. What are those ISs? Many DSSs are now closely intertwined with other organizational systems, including data warehouses, data marts, and ERP systems, from which they draw relevant data. 5. What is a sensitivity test?
A sensitivity analysis is conducted to test the degree to which the total profit grows or shrinks if one or more of the factors is increased or decreased. It is often referred to as what- if analysis.
6. The airline and hospitality industries use DSSs for yield management. What is yield management, and what is the output of a yield management DSS? The purpose of yield management DSSs is to find the proper pricing to maximize the overall revenue from selling seats for each flight. The result is often price discrimination. 7. What is the purpose of an expert system? How can it serve as a competitive tool? The purpose of ESs is to replicate the unstructured and undocumented knowledge of the few (the experts), and put it at the disposal of the many other people who need the knowledge, often novices or professionals in the same domain but with far less expertise. It can serve as a competitive tool by the using of a knowledge base, which is a collection of facts and the relationships among them. An ES does not use a model module but an inference engine. The inference engine is software that combines data that is input by the user with the data relationships stored in the knowledge base. The result is a diagnosis or suggestion for the best course of action. In most ESs, the knowledge base is built as a series of IF- THEN rules. 8. Explain how expert systems can distribute expertise.
By coupling quantitative data from a database with decision models. An expert system (ES) is developed to emulate the knowledge of an expert to solve problems and make decisions in a relatively narrow domain. 9. How could an ES be used to detect probable fraud committed by a bank...