1. © 2006 Prentice Hall, Inc.A – 1 Operations Management Module A – Decision-Making Tools © 2006 Prentice Hall, Inc. PowerPoint presentation for Operations Management Class Updated and extended by Prof. Dedeke

2. © 2006 Prentice Hall, Inc.A – 2 Outline  Fundamentals of Decision Making  Decision Tables  Types of Decision-Making Environments  Decision Making Under Uncertainty  Decision Making Under Risk  Decision Making Under Certainty  Expected Value of Perfect Information (EVPI)

3. © 2006 Prentice Hall, Inc.A – 3 Introduction  Decision Making Approaches  Structured  Unstructured

4. © 2006 Prentice Hall, Inc.A – 4 Structured Decision Making Process 1.Clearly define the problem and the factors that influence it 2.Develop the specific goals to be achieved 3.Develop quantitative measures that relate the goals to the problem 4.Develop alternate solutions to problem 5.Compare the alternate solutions using a model or structured methodology and the quantitative measures from step 3 6.Select the best alternative 7.Implement the decision and set a timetable for completion

5. © 2006 Prentice Hall, Inc.A – 5 Structured Process Applied (Comparing Options) 1.Problem: Make decision about value of a partnership 2.Goals: -Minimize cost of maintenance -Maximize financial benefits -Minimize risks to lifestyle 3.Measures: - Salary ($), cost for clothes, dating costs, IQ, family assets, health care costs 4.Alternatives & Data : How would you make the decision? MarySue Salary/yr $ 30,000 $ 80,000 Dating costs/yr $ 5,000 $ 20,000 Family assets $ 7 Million $ 800,000 Health care costs/yr $ 45,000 $ 3,000

6. © 2006 Prentice Hall, Inc.A – 6 Model for Decisions (Comparing Options) Problem: Make decision about value of a partnership 4. Certain Outcomes: -Maximize benefits (Whoever brings highest gains) (A) -Minimize costs (Whoever brings lowest costs) (B) -Minimize risks (C) 5. Resolution : How would you make the decision? A : B:C: MarySue Salary/yr $ 30,000 $ 80,000 Dating costs/yr $ 5,000 $ 20,000 Family assets $ 7 Million $ 800,000 Health care costs/yr $ 45,000 $ 3,000

7. © 2006 Prentice Hall, Inc.A – 7 Structured Process Applied 1.Careful: Worst approach is to add all the numbers together. Apples and oranges case! MarySue Salary/yr $ 30,000 $ 80,000 Dating costs/yr $ 5,000 $ 20,000 Family assets $ 7 Million $ 800,000 Health care costs/yr $ 45,000 $ 3,000

8. © 2006 Prentice Hall, Inc.A – 8 Decision Making Environment DecisionsunderuncertaintyDecisionsunder Risk (II) Decisionsunder Risk (I) Decisionsundercertainty Estimate-able Known Partial Total Value or Size of outcomes and consequences Level of confidence about occurrence of outcomes and consequences

9. © 2006 Prentice Hall, Inc.A – 9 Differentiating Decisions based on Outcomes  There is one position free. One candidate was interviewed. Position must be filled. The decision regarding who will receive offer of position can be made with _______________.  Likelihood of winning is certain.  There is one position free. Three candidates were interviewed. Position must be filled. The decision regarding who will receive offer of position can be made with _______________.  Likelihood of winning known.  There may be between zero and one free position. Position would be filled if profit is good and not filled if market is bad. Six candidates were interviewed. The decision regarding who will receive offer of the position can be made with ____________________.  Likelihood of winning known.  There could be zero to two positions free. Several candidates would be interviewed. Position would be filled if profit is good and not filled if market is bad. The decision regarding the hiring of one of the candidates interviewed can be made with _________________________. Likelihood of winning unknown.

10. © 2006 Prentice Hall, Inc.A – 10 Differentiating Decisions based on Outcomes  There is one position free. One candidate was interviewed. Position must be filled. The decision regarding who will receive offer of position can be made with __CERTAINTY__.  Likelihood of winning is certain.  There is one position free. Three candidates were interviewed. Position must be filled. The decision regarding who will receive offer of position can be made with __RISK I___.  Likelihood of winning known.  There may be between zero and one free position. Position would be filled if profit is good and not filled if market is bad. Six candidates were interviewed. The decision regarding who will receive offer of the position can be made with _RISK II__.  Likelihood of winning known.  There could be zero to two positions free. Several candidates would be interviewed. Position would be filled if profit is good and not filled if market is bad. The decision regarding the hiring of one of the candidates interviewed can be made with _UNCERTAINTY_______. Likelihood of winning unknown.

11. © 2006 Prentice Hall, Inc.A – 11 Decision-Making Environments  Decision making under uncertainty  Complete uncertainty as to which state of nature may occur  Decision making under risk  Several states of nature may occur  Each has a probability of occurring  Decision making under certainty  State of nature is known

12. © 2006 Prentice Hall, Inc.A – 12 Decision Making Under Certainty 1.EMV(A 1 ) = (1)($200,000) + (0)(-$180,000) = $200,000 2.EMV(A 2 ) = (1)($100,000) + (0)(-$90,000) = $100,000 States of Nature FavorableUnfavorable Alternatives Market Market Construct large plant (A1)$200,000-$180,000 Construct small plant (A2)$100,000-$90,000 Do nothing (A3)$0$0 Probabilities10 From Table A.3 The preferable option is A1 The preferable option is A1

13. © 2006 Prentice Hall, Inc.A – 13 Risk  Each possible state of nature has an assumed probability  States of nature are mutually exclusive  Probabilities must sum to 1  Determine the expected monetary value (EMV) for each alternative

14. © 2006 Prentice Hall, Inc.A – 14 Decision Making Under Risk 1.EMV(A 1 ) = (0.3)($200,000) + (0.7)(-$180,000) = -$66,000 2.EMV(A 2 ) = (0.3)($100,000) + (0.7)(-$90,000) = -$33,000 3.EMV(A 3 ) = (0.3)($0) + (0.7)($0) = $0 States of Nature FavorableUnfavorable Alternatives Market Market Construct large plant (A1)$200,000-$180,000 Construct small plant (A2)$100,000-$90,000 Do nothing (A3)$0$0 Probabilities0.30.7 From Table A.3 If A3 is excluded, The preferable option is A2 If A3 is excluded, The preferable option is A2

15. © 2006 Prentice Hall, Inc.A – 15 Decision Making Under Risk (2) In some cases the states of nature expected are certain, however the values of each states are uncertain. States of Demand Seasonal Ticket Occasional Alternatives Prob. Market Prob. Market Seasonal Ticket Occasional Alternatives Prob. Market Prob. Market Sell 100 tickets early (A1) 0.7 $200,000 0.3 $50,000 Sell 100 tickets later (A2) 0.7 $150,000 0.3 $300,000 Do nothing (A3) $0 $0 1.EMV(A 1 ) = (0.7)($200,000) + (0.3)($50,000) = $155,000 2.EMV(A 2 ) = (0.7)($150,000) + (0.3)($300,000) = $195,000 3.EMV(A 3 ) = (0)($0) + (0)($0) = $0 The preferable option is A2 The preferable option is A2 Case: Selling 100 tickets each time early or later in markets.

16. © 2006 Prentice Hall, Inc.A – 16 In-Class Exercise  Two suppliers deliver a product to us. Supplier 1 charges $ 575 for the part. The part seldom fails but its probability of failing is 0.1. The amount that we loose if part fails is $100.  Supplier 2 charges $ 550 for the same part. The probability of having a good part for this supplier is 0.8. The amount that we loose if a part fails is $460.  Find the expected monetary value of defective part from supplier 1?  Find the expected monetary value of defective part from supplier 2?  Find the total expected monetary value for each supplier?

17. © 2006 Prentice Hall, Inc.A – 17 In-Class Exercise: Response  Two suppliers deliver a product to us. Supplier 1 charges $ 575 for the part. The part seldom fails but its probability of failing is 0.1. The amount that we loose if part fails is $100.  Supplier 2 charges $ 550 for the same part. The probability of having a good part for this supplier is 0.8. The amount that we loose if a part fails is $460.  Find the expected monetary value of defective part from supplier 1? EMV defective part = $100*0.1 = $10  Find the expected monetary value of defective part from supplier 2? EMV defective part = $460*(1-0.8) = $92  Find the total expected monetary value for each supplier?

18. © 2006 Prentice Hall, Inc.A – 18 In-Class Exercise: Response States Good Parts Defective Parts Alternatives Prob. Cost Prob. Cost Good Parts Defective Parts Alternatives Prob. Cost Prob. Cost Supplier 1 (A1) 0.9 $575 0.1 $(100+575) Supplier 2 (A2) 0.8 $550 0.2 $(460+550) 1.EMV(A 1 ) = (0.9)($575) + (0.1)($675) = $585 2.EMV(A 2 ) = (0.8)($550) + (0.2)($1010) = $642 The preferable option is A1 The preferable option is A1 Find the total expected monetary value for each supplier?

19. © 2006 Prentice Hall, Inc.A – 19 Expected Monetary Value EMV (Alternative i) = (Payoff of 1 st state of nature) x (Probability of 1 st state of nature) + (Payoff of 2 nd state of nature) x (Probability of 2 nd state of nature) +…+ (Payoff of last state of nature) x (Probability of last state of nature)

20. © 2006 Prentice Hall, Inc.A – 20 Decision Making Under Uncertainty States of Nature FavorableUnfavorableMaximumMinimumRow AlternativesMarketMarketin Rowin RowAverage Construct large plant $200,000-$180,000$200,000-$180,000$10,000 Construct small plant $100,000 -$20,000$100,000 -$20,000$40,000 Do nothing $0$0$0$0$0 1.Maximax choice is to construct a large plant 2.Maximin choice is to do nothing 3.Equally likely choice is to construct a small plant Maximax Maximin Equally likely Probability unknown unknown

21. © 2006 Prentice Hall, Inc.A – 21 What is fixed cost?What is fixed cost? What is variable cost?What is variable cost? Revenues = Selling price * Volume soldRevenues = Selling price * Volume sold Total cost = Fixed cost ($) + (Variable cost ($) * Demand or Sale units (V)Total cost = Fixed cost ($) + (Variable cost ($) * Demand or Sale units (V) Profit (Payoff $) = Revenues ($) – Fixed cost ($) - (Variable cost ($) * Demand units (V)Profit (Payoff $) = Revenues ($) – Fixed cost ($) - (Variable cost ($) * Demand units (V) Decision Making

22. © 2006 Prentice Hall, Inc.A – 22 We desire to make a toy bicycle. We have two designs. Design A has fixed cost of $100,000, its variable unit cost is $5 and its demand units could be 25,000 or 150,000.We desire to make a toy bicycle. We have two designs. Design A has fixed cost of $100,000, its variable unit cost is $5 and its demand units could be 25,000 or 150,000. Design B has fixed cost of $300,000, its variable unit cost is $3 and its demand units could be 25,000 or 150,000.Design B has fixed cost of $300,000, its variable unit cost is $3 and its demand units could be 25,000 or 150,000. Probability of heavy demand is 0.7. Selling price per unit is $10.Probability of heavy demand is 0.7. Selling price per unit is $10. What is the payoff table for the decision?What is the payoff table for the decision? Profit (Payoff $) = Revenues ($) – Fixed cost ($) - (Variable cost ($) * Demand units (V)Profit (Payoff $) = Revenues ($) – Fixed cost ($) - (Variable cost ($) * Demand units (V) Example: Decision Making

23. © 2006 Prentice Hall, Inc.A – 23 We desire to make a toy bicycle. We have two designs. Design A has fixed cost of $100,000, its variable unit cost is $5 and its demand units could be either 25,000 (low demand) or 150,000 (high demand).We desire to make a toy bicycle. We have two designs. Design A has fixed cost of $100,000, its variable unit cost is $5 and its demand units could be either 25,000 (low demand) or 150,000 (high demand). Design B has fixed cost of $300,000, its variable unit cost is $3 and its demand units could be 25,000 (low demand) or 150,000 (high demand).Design B has fixed cost of $300,000, its variable unit cost is $3 and its demand units could be 25,000 (low demand) or 150,000 (high demand). Probability of heavy demand is 0.8. Price $10 per unit.Probability of heavy demand is 0.8. Price $10 per unit. What is the payoff table for the decision?What is the payoff table for the decision? Profit (Payoff $) = Revenues ($) – Fixed cost ($) - (Variable cost ($) * Demand units (V)Profit (Payoff $) = Revenues ($) – Fixed cost ($) - (Variable cost ($) * Demand units (V) Design ADesign A Payoff I = 25,000*10$ – $100,000 - ($5* 25,000)= $25,000Payoff I = 25,000*10$ – $100,000 - ($5* 25,000)= $25,000 Payoff II = 150,000*10$ – $100,000 - ($5* 150,000)= $650,000Payoff II = 150,000*10$ – $100,000 - ($5* 150,000)= $650,000 Design BDesign B Payoff I = 25,000*10$ – $300,000 - ($3* 25,000)= -$125,000Payoff I = 25,000*10$ – $300,000 - ($3* 25,000)= -$125,000 Payoff II = 150,000*10$ – $300,000 - ($3* 150,000)= $750,000Payoff II = 150,000*10$ – $300,000 - ($3* 150,000)= $750,000 Example: Deriving Payoff data for Decision Table

24. © 2006 Prentice Hall, Inc.A – 24 Example: Creating Decision Table Using Calculated Payoff Data 1.EMV(A 1 ) = 2.EMV(A 2 ) = States of Nature LightHigh Alternatives Market Market Design A (A1)$25,000$650,000 Design B (A2)-$125,000$750,000 Probabilities0.30.7 The preferable option is AXX

25. © 2006 Prentice Hall, Inc.A – 25 Using Decision Trees to Solve Decision Making Under Risk 1. Decision trees are ideal for decisions with sequential relationships 2.Symbols used in a decision tree: a.  —decision node from which one of several alternatives may be selected b.  —a state-of-nature node out of which one state of nature will occur

26. © 2006 Prentice Hall, Inc.A – 26 Decision Tree Example Favorable market Unfavorable market Favorable market Unfavorable market Construct small plant Do nothing A decision node A state of nature node Construct large plant Figure A.1

27. © 2006 Prentice Hall, Inc.A – 27 Decision Table Example State of Nature AlternativesFavorable MarketUnfavorable Market Construct large plant$200,000–$180,000 Construct small plant$100,000–$ 20,000 Do nothing$ 0 $ 0 Table A.1

28. © 2006 Prentice Hall, Inc.A – 28 Decision Tree Example = (.5)($200,000) + (.5)(-$180,000) EMV for node 1 = $10,000 EMV for node 2 = $40,000 = (.5)($100,000) + (.5)(-$20,000) Payoffs$200,000 -$180,000 $100,000 -$20,000 $0 Construct large plant Construct small plant Do nothing Favorable market (.5) Unfavorable market (.5) 1 Favorable market (.5) Unfavorable market (.5) 2 Figure A.2

29. © 2006 Prentice Hall, Inc.A – 29 In-Class Decision Tables to Decision Tree Exercise

30. © 2006 Prentice Hall, Inc.A – 30 Exercise 1: Find and Circle all Problems With This Decision Tree = (.5)($200,000) + (.5)(-$50,000) EMV for node 1 = $10,000 EMV for node 2 = $40,000 = (-0.5)($40,000) + (-0.5)(-$10,000) Payoffs $80,000 -$50,000 $40,000 -$10,000 $0 Construct large plant Construct small plant Do nothing Favorable market (.60) Favorable market (0.5) 1 Favorable market (-0.5) Unfavorable market ( -0.5) 2 Figure A.2

31. © 2006 Prentice Hall, Inc.A – 31 In-class Exercise 2: Find the EMVs for all options of the Decision Tree $100,000 -$50,000 $60,000 -$10,000 $0 Construct medium plant Construct small plant Do nothing Favorable market (.60) Unfavorable market 2 Favorable market (0.6) Unfavorable market 3 Figure A.2 Favorable market (.60) Unfavorable market 1 Construct large plant $140,000-$70,000

32. © 2006 Prentice Hall, Inc.A – 32 Complex Decision Tree Example Figure A.3

33. © 2006 Prentice Hall, Inc.A – 33 Decision Trees in Ethical Decision Making  Maximize shareholder value and behave ethically  Technique can be applied to any action a company contemplates

34. © 2006 Prentice Hall, Inc.A – 34YesNo Yes No Decision Trees in Ethical Decision Making Yes Is it ethical? (Weigh the affect on employees, customers, suppliers, community against shareholder benefit) No Is it ethical not to take action? (Weigh the harm to shareholders vs. the benefits to other stakeholders) Do it Don’t do it Do it, but notify appropriate parties Don’t do it No Yes Does action maximize company returns? Is action legal? Figure A.4

35. © 2006 Prentice Hall, Inc.A – 35 Operations decisions often involve selection of suppliers, vendors, markets, products and so on. In most of these cases, one has to define priorities.Operations decisions often involve selection of suppliers, vendors, markets, products and so on. In most of these cases, one has to define priorities. StepsSteps –Identify attributes to rank or compare, e.g. skill, age –Have a scale to use for ranking, e.g. 1, 2, 3, 4, 5 –Choose a scale for priorities, e.g. 0.1, 0.3, 0.9… –Use a system to compare alternatives Qualitative Decision Making: Factoring Priorities

36. © 2006 Prentice Hall, Inc.A – 36 Example: Priorities and Decision Making Employee A Employee B Attributes Weight (W) Score (S 1 ) W x S 1 Score (S 2 ) W x S 2 Language0.1106 Analytical0.2568 Technical0.3079 Salary Expect. 0.2056 Degree0.15105 TOTAL

37. © 2006 Prentice Hall, Inc.A – 37 Example: Priorities and Decision Making Employee A Employee B Weight (W) Score (S 1 ) W x S 1 Score (S 2 ) W x S 2 Language0.110160.6 Analytical0.2561.582 Technical0.3072.192.7 Salary Expect. 0.205161.2 Degree0.15101.550.75 TOTAL1.07.17.25

38. © 2006 Prentice Hall, Inc.A – 38 Review Chapter 8, Example 1, page 253-254 & 258 Solved problem 8.1, page 263Review Chapter 8, Example 1, page 253-254 & 258 Solved problem 8.1, page 263 See problem 8.1 in Excel spreadsheet Qualitative Decision Making: Location Strategies

39. © 2006 Prentice Hall, Inc.A – 39 Exercise 3: Transform the Qualitative Scores into Quantitative and Determine the Better Candidate Employee A Employee B Weight (W) Score (S 1 ) W x S 1 Score (S 2 ) W x S 2 Language0.15Excellent Very Good Analytical0.20 Excellent Technical0.15Fair Work Exp. 0.15 Very Good Fair GPA0.20Good People skills 0.15 Very Good Good TOTAL1.0