CHAPTER 2 Decision Making Systems Modeling and Support

CHAPTER 2 Decision Making, Systems, Modeling, and Support 1

Outline n n n n Introduction System Modeling How decision Cognition Decision makers Summary 2

1. Introduction · Decision making is a process of choosing among alternative courses of action for the purpose of attaining a goal or goals. · Decision making and problem solving there are four phases in this part. These phases are Intelligence, design, choice and implementation. · Decision making disciplines Behavioral disciplines include philosophy, psychology…. , and scientific disciplines include economics, statistic, decision analysis…… 3

1. 1 Some Concepts in Decisions of Enterprise The decision may be made by a group n Group members may have biases n There are several possibly conflicting objectives n Decision makers are interested in evaluating what-if scenarios n …. etc. n 4

2. Systems n What is systems? A system is a collection of objects such as people, resources, concepts, and procedures intended to perform an identifiable function or to serve a goal n Level (or Hierarchy) this concept reflects that all systems are actually subsystems because all are contained within some larger system. 5

2. 1 The structure of a system Three distinct parts of systems (Figure 2. 1) n Inputs are elements that enter the system. n Processes Process are all elements necessary to convert or transform input into outputs. n Outputs outputs are the finished products or the consequences of being in the system. Besides these… Three parts are surrounded by an environment and often include a feedback mechanism. In addition , a human decision maker is considered part of the system. 6

2. 2 One way to identify the elements of the environment Two questions： (Churchman, 1975) 1. Does the element matter relative to the system’s goals? [YES] 2. Is it possible for the decision maker to significantly manipulate this elements? [NO] 7

2. 3 The Boundary n n A system is separated from its environment by a boundary. The system is inside the boundary , whereas the environment lies outside. 8

2. 4 Closed and Open Systems n Closing the system Because every system is a subsystem of another, the system analysis process may never end. So, we must confine the system analysis to defined, manageable, boundaries. And this confinement is call “closing the system” n Closed System A closed system is totally independent from other subsystems or systems. n Open System An open system is very dependent on its environment. And it accepts inputs from the environment and may deliver outputs to the environment. 9

2. 5 Information System n An information system collects , processes , stores , analyzes , and disseminates information for a specific purpose. And the information system often located in core section. 10

3. Models Simplified representation or abstract n The reality is too complex n The classification of models： n 1. Iconic models 2. Analog models 3. Mathematical models 11

3. 1 The benefits of Models 1. Compression of time 2. Model manipulation is easier than real system 3. Lower cost 4. Lower cost in trial-and-error experiment 5. Be used to estimate the risks 6. Analyzing large number of possible solutions 7. Help learning & training 12

3. 2 The Modeling Process Solution Approaches n n Trial-and-error Simulation Optimization Heuristics Decision-Making Process (Simon, 1977) n n Intelligence phase Design phase Choice phase Implementation phase (Figure 2. 2) 13

3. 3 The Intelligence Phase 1. Finding the Problem 2. Problem Classification －Programmed vs Nonprogrammed problems 3. Problem Decomposition 4. Problem Ownership 14

3. 4 The Design Phase Finding, developing, and analyzing courses of action n Construct, test, validate a model of decision-making n Model－conceptualization of problem abstraction to quantitative/qualitative forms n 15

n Some topics of modeling (relate to quantitative model) 1. The components of the model 2. The structure of the model 3. Selection of a principle of choice 4. Developing alternatives 5. Predicting outcomes 6. Measuring outcomes 7. Scenarios 16

3. 4. 1 The Component of Quantitative Model Uncontrollable variables Decision Mathematical Result Variables relationships variables 17

Variables Area Financial investment Marketing n Decision Result Variables Investment Total amounts profit Where to Market advertise share Uncontrollable variables Inflation rate Customer’s income Intermediate Result Variables 18

3. 4. 2 The Structure of Quantitative Models The Product-Mix Linear Programming Model n n n MBI Corporation Decision: How many computers to build next month? Two types of computers Labor limit Materials limit Marketing lower limits Constraint Labor (days) Materials $ Units Profit $ CC 7 300 10, 000 1 8, 000 CC 8 500 15, 000 1 12, 000 Rel <= <= >= >= Max Limit 200, 000 / mo 8, 000/mo 100 200 Objective: Maximize Total Profit / Month 19

Linear Programming Model n Components Decision variables X 1, X 2 Result variable Z Uncontrollable variables (constraints) n Solution X 1 = 333. 33 X 2 = 200 Profit = $5, 066, 667 20

3. 4. 3 Selection of a Principle of Choice n Describe the acceptability of a solution approach 1. Normative models 2. Suboptimization 3. Descriptive models 4. Good enough or satisficing ※Bounded rationality 21

3. 4. 4 Developing (Generating) Alternatives It’s necessary to generate alternatives manually n Searching & creativity－Taking time & costing money n Searching comes after the criteria for evaluating the alternatives n 22

3. 4. 5 Predicting the Outcome of Each Alternative Classify the knowledge into three categories ←Increasing knowledge Complete Risk Ignorance knowledge Decreasing knowledge→ 23

n Decision Making Under Certainty The decision maker is a perfect predictor of the future n Decision Making Under Risk The decision maker have to consider possible outcomes for each alternative Calculating and selecting the best expected value of an alternative → Risk Analysis n Decision Making Under Uncertainty The decision maker doesn’t know about possible outcomes 24

3. 4. 6 Measuring Outcomes n For example： Profit is an outcome Profit maximization is a goal ※ But units of outcomes and goals are the same 25

3. 4. 7 Scenarios A statement of assumptions about the operating environment of a system n Be helpful in simulation & what-if analysis n In MSS, scenarios play an important role. (Potential opportunities, problem areas, flexibility in planning) n 26

3. 5 The Choice Phase n Search Approaches ─ Analytical techniques are used mainly for solving structured problems ─ Algorithms Analytical techniques may use algorithms to increase the efficiency of the search. ─ Blind and heuristic search approach Blind: blind research techniques are arbitrary approaches that are not guided Heuristic search approach: it can reduce the amount of necessary computations. 27 AHP reference

3. 6 Evaluation: Multiple Goals, Sensitivity Analysis, What-If, and Goal Seeking n Multiple goals: Today’s management systems are much more complex, and one with a single is few. Instead, managers want to attain simultaneous goals, where some of them conflict. Conflicts？ 28

n Sensitivity Analysis: ─ Automatic sensitivity analysis Sensitivity analysis attempts to assess the impact of a change in the input data or parameters on the proposed solution. ─ Trial and error It is usually limited to one change at a time, and only for certain variables. 29

n Trial and Error: ─ What-if analysis (Figure 2. 9) If you change one of unit revenue, or unit cost, or initial sales or sales growth rate , you will know the end of the annual net profit. ─ Goal seeking (Figure 2. 10) Goal-seeking analysis calculates the values of inputs necessary to achieve a desired level of an output 30

3. 7 The Implementation Phase At more than 400 years ago , Machiavelli said: 『 “nothing more difficult carry out , nor more doubtful of success , nor more dangerous to handle , than to initiate a new order of things. ” 』 31

4. How Decisions Are Supported Intelligence Design Choice Implementation ANN MIS EIS GDSS ANN Management science GDSS 32

n Intelligence: DSS can support this phase to scan external and internal information sources for opportunities. n Design: DSS has this capability of generating alternative course of action, discussing the criteria for choice. n Choice: DSS can support the choice phase through the what-if and goalseeking analysis. n Implement: Implementation phase DSS benefits are partly due to the vividness and detail of the analysis and displayed output. 33

5. Cognitive n Cognition theory Cognition is the set of activities. n Cognitive style It is the subject process through which people perceive , organize, change information during the decision-making process. n Decision style (table 2. 4) Decision style is the manner in which decision makers think and react to problems. 34

6. The Decision Makers Individual n Group n 35

7. Summary Managerial making is synonymous with the whole process of management n Problem solving is also opportunity evaluation n Systems can be open , interacting with their environment , or closed. n …. etc n 36

environment output(s) input(s) 轉換過程 feedback boundary 37