Scribd
Upload
156 views

Quamet2 Lesson 3.1

Decision trees can represent problems involving sequential decisions with uncertainty. They contain decision nodes, where a choice can be made, and chance nodes, where a random outcome occurs. Five steps are used to analyze decision trees: 1) define the problem, 2) structure the tree, 3) assign probabilities, 4) estimate payoffs, and 5) compute expected monetary values to determine the optimal decision. Thompson Lumber considered conducting a market survey before building a plant. The expected value of sample information was calculated to determine if the survey was worthwhile, and it exceeded the $10,000 cost, so the survey should be conducted.

Uploaded by

Juan Rafael Fernandez
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PDF, TXT or read online on Scribd
156 views

Quamet2 Lesson 3.1

Decision trees can represent problems involving sequential decisions with uncertainty. They contain decision nodes, where a choice can be made, and chance nodes, where a random outcome occurs. Five steps are used to analyze decision trees: 1) define the problem, 2) structure the tree, 3) assign probabilities, 4) estimate payoffs, and 5) compute expected monetary values to determine the optimal decision. Thompson Lumber considered conducting a market survey before building a plant. The expected value of sample information was calculated to determine if the survey was worthwhile, and it exceeded the $10,000 cost, so the survey should be conducted.

Uploaded by

Juan Rafael Fernandez
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 17

Decision Trees

Lesson 3.1

Decision Trees

Any problem that can be presented in a decision table can also be graphically represented in a decision tree Decision trees are most beneficial when a sequence of decisions must be made All decision trees contain decision points or nodes and state-of-nature points or nodes

A decision node from which one of several alternatives may be chosen A state-of-nature node out of which one state of nature will occur
Operations Research - Asia Pacific College 2

9 October 2010

Five Steps to Decision Tree Analysis


1. 2. 3. 4. Define the problem Structure or draw the decision tree Assign probabilities to the states of nature Estimate payoffs for each possible combination of alternatives and states of nature 5. Solve the problem by computing expected monetary values (EMVs) for each state of nature node
9 October 2010 3

Operations Research - Asia Pacific College

Structure of Decision Trees


Trees start from left to right Represent decisions and outcomes in sequential order Squares represent decision nodes Circles represent states of nature nodes Lines or branches connect the decisions nodes and the states of nature

9 October 2010

Operations Research - Asia Pacific College

Thompsons Lumber - Expected Monetary Value ( EMV )


STATE OF NATURE ALTERNATIVE Construct a large plant Construct a small plant Do nothing Probabilities FAVORABLE MARKET ($) 200,000 100,000 0 0.50 UNFAVORABLE MARKET ($) 180,000 20,000 0 0.50 EMV ($) 10,000 40,000 0

9 October 2010

Operations Research - Asia Pacific College

Thompsons Decision Tree


A State-of-Nature Node
Favorable Market

A Decision Node
t uc ant tr l ns e P Co arg L

Unfavorable Market

Favorable Market

Construct Small Plant


Do No th in g

Unfavorable Market

9 October 2010

Operations Research - Asia Pacific College

Thompsons Decision Tree


EMV for Node 1 = $10,000 Alternative with best EMV is selected
t uc ant tr l ns e P Co arg L

= (0.5)($200,000) + (0.5)($180,000)
Payoffs Favorable Market (0.5) $200,000

Unfavorable Market (0.5)

$180,000

Favorable Market (0.5)

$100,000 $20,000

Construct Small Plant


Do No th in g

Unfavorable Market (0.5) EMV for Node 2 = $40,000

= (0.5)($100,000) + (0.5)($20,000)
$0

9 October 2010

Operations Research - Asia Pacific College

Example 3.1 P&Gs Tide I

Alfred is the Product Manager of Tide and he is planning to launch a new product. He can either launch Tide with Zonrox, Tide with Downy, or not do anything at all. He was able to determine the expected payoff depending on the decision and the type of the market, successful or a failure. The probability is 60% that the market is successful and 40% that the market is a failure. The figures are summarized in the following table. What should Alfred launch? How much gain or loss does he expect for the company?
Operations Research - Asia Pacific College 8

9 October 2010

Example 3.1 P&Gs Tide I


TYPE OF MARKET New Product Payoff ($000) Tide with Zonrox Tide with Downy Do nothing Probabilities Successful ($) 20 12 0 0.60 Failure ($) -18 -3 0 0.40

9 October 2010

Operations Research - Asia Pacific College

Example 3.1 P&Gs Tide I


Payoffs Succesful Market (0.6) $20,000

1
ith w de rox Ti on Z

Failure Market (0.4)

$18,000

Favorable Market (0.6)

$12,000 $3,000

Tide with Downy


Do No th in g

Unfavorable Market (0.4)

$0
9 October 2010 Operations Research - Asia Pacific College 10

Thompsons Decision Tree with Conditional Probabilities

When sequential decisions need to be made, decision trees are more powerful tools than decision tables. Suppose that before deciding about building a new plant, John has the option of conducting his own marketing survey, at a cost of $10,000. (This cost are subtracted from payoffs.) There is a 45% chance that the survey results will indicate a favorable market and 55% chance the results will be negative. Conditional probabilities of market types depending on survey results are calculated. This will be shown in next lesson.
Operations Research - Asia Pacific College 11

9 October 2010

Thompsons Complex Decision Tree


First Decision Point Second Decision Point
nt Pla ge Lar Small Plant

Payoffs Favorable Market (0.78) Unfavorable Market (0.22) Favorable Market (0.78) Unfavorable Market (0.22) No Plant Favorable Market (0.27) Unfavorable Market (0.73) Favorable Market (0.27) Unfavorable Market (0.73) No Plant $190,000 $190,000 $90,000 $30,000 $10,000 $190,000 $190,000 $90,000 $30,000 $10,000

2 3

M ar ke t

5) .4 (0 ey lts le v ur esu rab S o Su R Fav 1 r ve Re y ( Ne su 0.5 5) g a lt s t iv e

ve y

nt Pla ge Lar Small Plant

Su r

4 5

Co

nd uc t

Do

No t

Co n duc t Su rve y

t lan eP g Lar Small Plant

6 7

Favorable Market (0.50) Unfavorable Market (0.50) Favorable Market (0.50) Unfavorable Market (0.50) No Plant

$200,000 $180,000 $100,000 $20,000 $0

9 October 2010

Operations Research - Asia Pacific College

12

Thompsons Complex Decision Tree


1. Given favorable survey results,
EMV(node 2) = EMV(large plant | positive survey) = (0.78)($190,000) + (0.22)($190,000) = $106,400 EMV(node 3) = EMV(small plant | positive survey) = (0.78)($90,000) + (0.22)($30,000) = $63,600 EMV for no plant = $10,000

2. Given negative survey results,


EMV(node 4) = EMV(large plant | negative survey) = (0.27)($190,000) + (0.73)($190,000) = $87,400 EMV(node 5) = EMV(small plant | negative survey) = (0.27)($90,000) + (0.73)($30,000) = $2,400 EMV for no plant = $10,000

9 October 2010

Operations Research - Asia Pacific College

13

Thompsons Complex Decision Tree


3. Compute the expected value of the market survey,
EMV(node 1) = EMV(conduct survey) = (0.45)($106,400) + (0.55)($2,400) = $47,880 + $1,320 = $49,200

4. If the market survey is not conducted,


EMV(node 6) = EMV(large plant) = (0.50)($200,000) + (0.50)($180,000) = $10,000 EMV(node 7) = EMV(small plant) = (0.50)($100,000) + (0.50)($20,000) = $40,000 EMV for no plant = $0

5. Best choice is to seek marketing information

9 October 2010

Operations Research - Asia Pacific College

14

Thompsons Complex Decision Tree


First Decision Point Second Decision Point $106,400 Favorable Market (0.78) Unfavorable Market (0.22) nt Pla ge $63,600 Favorable Market (0.78) Lar Small Unfavorable Market (0.22) Plant No Plant $87,400 Favorable Market (0.27) Unfavorable Market (0.73) ant Favorable Market (0.27) Unfavorable Market (0.73) No Plant Payoffs $190,000 $190,000 $90,000 $30,000 $10,000 $190,000 $190,000 $90,000 $30,000 $10,000

$49,200 C

on du ct

$2,400

M ar ke t

5) .4 (0 ey lts le v ur esu rab S o Su R Fav rv e Re y ( Ne su 0.5 5) g a lt s t iv e

Su r

ve y

$106,400

l eP $2,400 arg L Small Plant

Do

$10,000
No t

Favorable Market (0.50) Unfavorable Market (0.50) Favorable Market (0.50) Unfavorable Market (0.50) No Plant

$40,000

Co n duc t Su rve y

t lan e P $40,000 g Lar Small Plant

$200,000 $180,000 $100,000 $20,000 $0

9 October 2010

Operations Research - Asia Pacific College

15

Expected Value of Sample Information

Thompson wants to know the actual value of doing the survey


EVSI =
Expected value with sample information, assuming no cost to gather it

Expected value of best decision without sample information

= (EV with sample information + cost) (EV without sample information) EVSI = ($49,200 + $10,000) $40,000 = $19,200

9 October 2010

Operations Research - Asia Pacific College

16

Thompsons Decision on Market Survey

This means that Thompson Lumber Company could have paid up to $19,200 for a market study and still come out ahead. Since it costs $10,000, the survey is indeed worthwhile.

9 October 2010

Operations Research - Asia Pacific College

17

You might also like