Narsee Monjee Institute of Management Studies (Deemed University)

FTMBA : (Decision Analysis)

Hand out No. 3 Decision Tree
1. An oil drilling company is considering purchase of mineral rights on a property for Rs.100 lakh. The price
includes tests to indicate whether property has type A geological formation or type B geological formation.
The company will be unable to tell the type of geological formation until the purchase is made. It is known,
however, that 40 per cent of the land in this area has type A formation, and 60 per cent type B formation. If
the company decides to drill on land, it will cost Rs.200 lakh. If the company does drill, it may hit an oil
well, gas well, or a dry hole. Drilling experience indicates that the probability of striking an oil well is 0.4
on type A and 0.1 on type B formation. Probability of hitting gas is 0.2 on type A and 0.1 on type B
formation. The estimated discounted cash value of income from an oil well is Rs.1,000 lakh and that from a
gas well is Rs.500 lakh. This includes everything except cost of mineral rights and cost of drilling. Use
decision tree approach and recommend whether the company should purchase the mineral rights.
0.4
Oil
700
0 700

0.2
Drill Gas
200
0 200 0 200

0.4 0.4
Type A Dry
1 -300
0 200 0 -300

Do not drill
-100
0 -100

0.1
Purchase Oil
700
0 20 0 700

0.1
Drill Gas
200
0 -150 0 200

0.6 0.8
Event 11 Dry
1 2 -300
20 0 -100 0 -300

Do not drill
-100
0 -100

Do not Purchase
0
0 0
2. The Oil India Corporation (OIC) is considering whether to go for an offshore oil drilling contract to be
awarded in Bombay High. If OIC bid, value would be Rs 600 million with a 65% chance of gaining the
contract. The OIC may set up a new drilling operation or move already existing operation, which has proved
successful, to a new site. The probability of success and expected returns are a follows:
Outcome New drilling operation Existing Operation
Probability Expected revenue Probability Expected revenue
(Rs million) (Rs million)
Success 0.75 800 0.85 700
Failure 0.25 200 0.15 350
In the Corporation do not bid or lose the contract, the can use Rs 600 million to modernise their operation.
This would result in a return of either 5 percent or 8 percent on the sum invested with probabilities 0.45 and
0.55. (Assume that all costs and revenue have been discounted to present value.)
(a) Construct a decision tree for the problem showing clearly the courses of action.
(b) By applying an appropriate decision criterion recommend whether or not the Oil India Corporation should
bid the contract.
 0.75
Success
200
New drilling 0 200

0 50 0.25
Failure
0.65 -400
Gets Bid 0 -400
1
0 50 0.85
Success
100
Existing Drilling 0 100

Bid 0 47.5 0.15

Failure
0 46.465 -250
0 -250

0.45
5%
0.35 30
Do not get bid Modernise 0 30
1
1 0 39.9 0 39.9 0.55
46.465 8%
48
0 48

0.45
5%
30
Do not Bid Modernise 0 30
1
0 39.9 0 39.9 0.55
8%
48
0 48
3. Mr. Pankaj wants to invest Rs. 50 lakhs for a period of one year, and has the following options
 Invest in fixed deposits which will yield constant annual interest of , say 9.5%
 Invest in a property in city. The property rates may increase, and the property may fetch Rs. 60
Lakhs at the end of the year, with the probability of 0.5. But, the property prices might not increase so
much and might fetch Rs 55 Lakhs at the end of the year. The probability of this happening is 0.3. The
property rate may remain unchanged and the property might fetch only Rs 50 Lakhs. The probability for
this is 0.2
 Invest in a property in the suburb of the city. If the suburb grows, the property might give good
profit, otherwise the rate of the property might even decline. The chance that the investment will give Rs
70 Lakhs is 30% , and the chance that the investment will be just worth Rs. 35 Lakhs is 70%.
 Invest in mutual funds. If the stock market is good, it might be worth Rs. 57 Lakhs; otherwise
it might be worth only Rs. 52 Lakhs. The chances that the market might be good or otherwise is 60% and
40% ,respectively. Help Pankaj take appropriate decision.
 Fixed deposit
4.75
0 4.75

0.5

10
0 10

0.3
Property in city
5
0 6.5 0 5

0.2

0
2 0 0
6.5
0.3

20
property in suburb 0 20

0 -4.5
0.7
-15
0 -15

0.6

7
MF 0 7

0 5
0.4
2
0 2
4. Raman Industries Ltd has a new product which they expect has great potential. At the moment they have
two courses of action open to them: To test market (S 1) and to drop product (S 2). If they test it, it will cost
Rs 50,000 and the response could be positive or negative with probabilities 0.70 and 0.30, respectively. If it
is positive, they could either market it with full effort or drop the product.
If they market with full scale, then the result might be low, medium, or high
demand and the respective net payoffs would be – Rs 1,00,000, Rs 1,50,000/- or Rs 5,00,000. These outcomes
have probabilities of 0.25, 0.55 and 0.20, respectively. If the result of the test marketing is negative they
have decided to drop the product. If, at any point, they drop the product there is a net gain of Rs 25,000 from
the sale of scrap. All financial values have been discounted to the present. Daw a decision tree for the
problem and indicate the most preferred decision.
0.25
Low
50000
0 50000

0.55
Market Medium
100000
0 157500 0 100000

0.7 0.2
Positive High
1 450000
0 157500 0 450000

Test Drop
-25000
0 102750 0 -25000

0.3
negative Drop
1 -25000
102750 0 -25000

Drop
25000
0 25000
5. A manufacturing company has just developed a new product. On a basis of past experience, a product
such as this will either be successful, with an expected gross return of Rs 1,00,000, or unsuccessful, with an
expected gross return of Rs 20,000. Similar products manufactured by the company have a record of being
 successful about 50 percent of the time. The production and marketing costs of the new product are
expected to be Rs 50,000.
The company is considering whether to market this new product or to drop it.
Before making its decision, a test marketing effort can be conducted at a cost of Rs 10,000. Based on past
experience, test marketing results have been favourable about 70 percent of the time. Furthermore, products
favourably tested have been successful 80 percent of the time. However, when the test marketing result has
been unfavourable, the product has only been successful 30 percent of the time. What course of action
should the company pursue?
0.5
Success
50000
Market 0 50000

0 10000 0.5
Failure
No test -30000
1 0 -30000
0 10000

Drop
0
0 0

0.8
Success
40000
Market 0 40000
2
13800 0 24000 0.2
0.7 Failure
Fav -40000
1 0 -40000
0 24000

Drop
-10000
0 -10000
Test
0.3
0 13800 Success
40000
Market 0 40000

0 -16000 0.7
0.3 Failure
Unfav -40000
2 0 -40000
0 -10000

Drop
-10000
0 -10000
6. The XYZ Company manufacture guaranteed tennis balls. At present time, approximately 10 percent of the
tennis balls are defective. A defective ball leaving the factory costs the company Re 0.50 to honour its
guarantee. Assume that all defective balls are returned. At a cost of Re 0.10 per ball, the company can
conduct a test, which always correctly identifies both good and bad tennis balls.
(a) Draw a decision tree and determine the optimal course of action and its expected cost.
(b) At what test cost the company should be indifferent to testing?
Test
0.1
0 0.1

2 0.1
0.05 Defective
0.5
Don't Test 0 0.5

0 0.05 0.9
Nondefective
0
0 0
7. The Ore Mining Company is attempting to decide whether or not a certain piece of land should be
purchased. The land cost is Rs 3,00,000. If there are commercial ore deposits on the land, the estimated
value of property is Rs 5,00,000. If no ore deposits exist, however, the property value is estimated at Rs
2,00,000. Before purchasing the land, the property can be cored at a cost of Rs 20,000. The coring will
indicate if conditions are favourable or unfavourable for ore mining. If the coring report is favourable the
 probability of recoverable ore deposits on the land is 0.8, while if the coring report is unfavourable the
probability is only 0.2. Prior to obtaining any coring information, management estimates that the odds are
50-50 that ore is present on the land. Management has also received coring reports on pieces of land similar
to the ore in question and found that 60 percent of the coring reports were favourable.
Construct a decision tree and determine whether the company should purchase the land, decline to purchase it,
or take a coring test before making its decision. Specify the optimal course of action and EMV.
0.5
Ore
200000
Purchase 0 200000

0 50000 0.5
No Ore
Don't Test -100000
1 0 -100000
0 50000

don’t perchase
0
0 0

0.8
Ore
180000
Purchase 0 180000
2
64000 0 120000 0.2
0.6 No Ore
Fav -120000
1 0 -120000
0 120000

don’t perchase
-20000
0 -20000
Test
0.2
0 64000 Ore
180000
Purchase 0 180000

0 -60000 0.8
0.4 No Ore
Unfav -120000
2 0 -120000
0 -20000

don’t perchase
-20000
0 -20000
8. XYZ company dealing with a newly invented telephone device is faced with the problem of selecting out
of the following courses of action available:
(i) manufacture the device itself; or
(ii) be paid on a royalty basis by another manufacturer; or
(iii)sell the rights for its invention for a lump sum.
The profit (in Rs ‘000s) which can be expected in each and the probabilities associated with the level of
sales are shown in the following table:
Outcome Probability Manufacture itself Royalties Sell all rights
High sales 0.1 75 35 15
Medium sales 0.3 25 20 15
Low sales 0.6 -10 10 15
Represent the company’s problem in the form of a decision tree. Redraw further the decision tree by
introducing the following additional information:
(a) If it manufactures itself and sales are medium or high, then company has the opportunity of developing a
new version of its telephone;
(b) From past experience company estimates that there is a 50 percent chance of successful development,
(c) The cost of development is Rs 15 and returns after deduction of development cost are Rs 30 and Rs 10 for
high and medium sales, respectively.
 Sell Rights
15
0 15

0.1
High
35
0 35

0.3
Royalty Medium
20
0 15.5 0 20

0.6
Low
10
0 10

0.5
2 Success
15.5 105
Develop new 0 105

0 82.5 0.5
0.1 Failure
High 60
1 0 60
0 82.5

don’t develop
75
0 75

0.5
Success
35
Develop new 0 35
Market Self
0 22.5 0.5
0 9.75 0.3 Failure
Medium 10
2 0 10
0 25

don’t develop
25
0 25

0.6
Low
-10
0 -10
9. A farmer is considering drilling a well. In the past only 70% wells drilled were successful at 20 metres
depth in that area Moreover on finding no water at 20 metres, some person in that area drilled it up to 25
metres but only 20% struck water at that level. The prevailing cost of drilling is Rs. 500 per metre. The
farmer estimated that in case he does not get water in his own well he will have to pay Rs. 15000 to buy
water from outside for the same period of getting water from the well. Determine the farmer’s decision
strategy.
 Do not drill
15000
0 15000

0.8
no water
27500
drill next 5 mt 0 27500
2
14350 0 24500 0.2
0.3 water
no water 12500
1 0 12500
0 24500

Drill up to 20 mt stop
25000
0 14350 0 25000

0.7
water
10000
0 10000

10. A company is planning to open a super bazaar in a city. The company has selected three different
locations namely location A, B and C.
Location A is in the upper class dominated locality. Here, if the project is successful, it would give net profit
of Rs. 50 Lakhs per annum, but if the project is not successful, the company would lose Rs. 65 Lakhs.
Location B is in middle class dominated locality. Here, if the project is successful, the company would get net
profit of Rs 30 Lakhs per annum but if it fails it would have annual loss of Rs. 15 Lakhs.
The third location C is on the highway, little out of city. Here, if the project is successful, would yield net
profit of Rs 15 Lakhs, and if it is unsuccessful, it would result in neither profit nor loss.
The success of a project at each location is dependent on the retail industry. If the retail industry does well,
project at any location would be successful, and if the growth in the retail industry declines the project would
not be so successful irrespective of location. There is a 60% chance that the retail industry would grow. Given
this scenario, in which location should the company open the superbazaar? What should the company pay for
the perfect information about the growth of the retail industry?
0.6
Successful
50
Location A 0 50

0 4 0.4
unsuccessful
-65
0 -65

0.6
Successful
30
Location B 0 30
2
12 0 12 0.4
unsuccessful
-15
0 -15

0.6
Successful
15
Location C 0 15

0 9 0.4
unsuccessful
0
0 0
 Location A
50
0 50

0.6
Successful Location B
1 30
0 50 0 30

Location C
15
0 15

30
Location A
-65
0 -65

0.4
Unsuccessful Location B
3 -15
0 0 0 -15

Location C
0
0 0
11. In the above example, suppose, a consultant who has analysed the retail industry, and is ready to give
some more facts, for a fee of Rs 1 Lakh, approaches the company for soliciting his advice . The consultant
will state the prediction about the retail industry as either ‘Favorable’ or ‘Unfavourable’.
company analysed the past history of the predictions by the consultant, and found that 90% of the times the
industry showed growth, the consultant had predicted it correctly as favourable. This is the probability of
forecast being favourable given the industry showed growth. It is also given that, 80% of the times when the
consultant predicted that the industry would be Unfavourable, the industry did not show growth. Now what
should the company decide?

Test Ei p(Ei) p(Test/Ei) p(Test & Ei) p(Ei/test)

fav g 0.6 0.9 0.54 0.871
ng 0.4 0.2 0.08 0.129
1 0.62 1

un fav g 0.6 0.1 0.06 0.158

ng 0.4 0.8 0.32 0.842
1 0.38 1
 0.871
Successful
49
Location A 0 49

0 34.165 0.129
Unsuccessful
-66
0 -66

0.871
Successful
0.62 29
Consultant Predicts favorable Location B 0 29
1
0 34.165 0 23.195 0.129
Unsuccessful
-16
0 -16

0.871
Successful
14
Location C 0 14

0 12.065 0.129
Unsuccessful
-1
Hire consultant 0 -1

0 21.7029 0.158
Successful
49
Location A 0 49

0 -47.83 0.842
Unsuccessful
-66
0 -66

0.158
Successful
0.38 29
Consultant Predicts unfavorable
Location B 0 29
3
0 1.37 0 -8.89 0.842
Unsuccessful
-16
0 -16

0.158
1 Successful
21.7029 14
Location C 0 14

Do not hire consultant 0 1.37 0.842

Unsuccessful
0 0 -1
0 -1

12 A retailer must decide whether to build a small or a large facility at a new

location. Demand at the location can be either small or large, with probabilities estimated to be 0.4 and
0.6, respectively. If a small facility is built and demand proves to be high, the manager may choose not to
expand (payoff = $223,000) or to expand (payoff = $270,000). If a small facility is built and demand is
low, there is no reason to expand and the payoff is $200,000. If a large facility is built and demand proves
to be low, the choice is to do nothing ($40,000) or to stimulate demand through local advertising. The
response to advertising may be either modest or sizable, with their probabilities estimated to be 0.3 and
0.7, respectively. If it is modest, the payoff is estimated to be only $20,000; the payoff grows to $220,000
if the response is sizable. Finally, if a large facility is built and demand turns out be high, the payoff is
$80,000.
Draw a decision tree. Then analyze it to determine the expected payoff for each decision and event node.
Which alternative – building a small facility or building a large facility – has the higher expected payoff?
 0.4
Low demand
200000
0 200000
Small

0 242000 Do not expand

0.6 223000
High Demand 0 223000
2
0 270000
Expand
270000
0 270000

1
242000 Nothing
40000
0.4 0 40000
Low Demand
2 0.3
0 160000 Modest Response
20000
Local Advertising 0 20000

Large 0 160000 0.7

Sizeable Response
0 112000 220000
0 220000

0.6
High Demand
80000
0 80000

13. Evelyn Parkhill is considering three possible ways to invest the $200,000 she has just inherited.
(1) Some of her friends are considering financing a combined laundromat, video-game arcade, and
pizzeria, where the young singles in the area can meet and play while doing their laundry. This
venture is highly risky and could result in either a major loss or a substantial gain within a year.
Evelyn estimates that with probability 0.6, she will lose all of her money. However, with
probability 0.4, she will make a $200,000 profit.
(2) She can invest in some new apartments that are being built in town. Within 1 year, this fairly
conservative project will produce a profit of at least $10,000, but it might yield $15,000,
$20,000, $25,000, or possibly even $30,000. Evelyn estimates the probabilities of these five
returns at 0.20, 0.30, 0.25, 0.20. and 0.05, respectively.

(3) She can invest in some government securities that have a current yield of 8.25 percent.

(a) Construct a decision tree to help Evelyn decide how to invest her money.
(b) Which investment will maximize her expected 1-year profit?
(c) How high would the yield on the government bonds have to be before she would decide
to invest in them?
(d) How much would she be willing to pay for perfect information about the success of the
laundromat?
(e) How much would she be willing to pay for perfect information about the success of the
apartments?
 0.6
Fails
-200
Laundrymart 0 -200

0 -40 0.4
Success
200
0 200

0.2
Event 6
10
0 10

0.3
Event 7
15
0 15

2 0.25
18 Apartments Event 8
20
0 18 0 20

0.2
Event 9
25
0 25

0.05
Event 10
30
0 30

Gov. Bonds
16.5
0 16.5
b Invest in appartments
c more than 9%
d EPPI=90.8 , EVPI = 72.8
e EPPI = 19.75 , EVPI = 1.75

14. AFC is about to launch its new Wings ‘N Things fast food nationally. The research department is
convinced that Wings ‘N Things will be a great success and wants to introduce it immediately without
advertisement in all AFC outlets. The marketing department sees “things” differently and wants to unleash an
intensive advertisement campaign. The advertisement campaign will cost $100,000 and if successful will
produce $950,000 revenue. If the campaign is unsuccessful (there is a 30% chance it won’t be),The revenue is
estimated only $200000 if no advertisement is used. the revenue is estimated at only $400,000 with
probability .8 if the customers are receptive and $200,000 with probability .2 if they are not.
(a) Develop the associated decision tree.
(b) Determine the best course of action for AFC.
0.8
Receptive
400000
without ad 0 400000

0 360000 0.2
non recpt
200000
0 200000
2
625000 0.7
Succ
850000
with ad 0 850000

0 625000 0.3
non succ
100000
0 100000
AFC management has decided to test-market its Wings ‘N Things in selective locations. The outcome of the
test is either “good” (a1) or “bad” (a2). The test yields the following conditional probabilities with and without
the advertisement campaign:
a1 a2 a1 a2
v1 .95 .05 w1 .8 .2
v2 .3 .7 w2 .4 .6

The symbols v1 and v2 represent “success” and “no success,” and w 1 and w2 represent “receptive”
and “not receptive.”
(c) Develop the associated decision tree.
(d) Determine the best course of action for AFC.
Without Ad camp
fore event p(ev) p(fore/ev) p(fore & ev) p(ev/fore)
good rec 0.8 0.8 0.64 0.888889 0.888889
non rec 0.2 0.4 0.08 0.111111 0.111111
0.72
bad rec 0.8 0.2 0.16 0.571429 0.571429
non rec 0.2 0.6 0.12 0.428571 0.428571
0.28
With Ad Camp
good suc 0.7 0.95 0.665 0.880795 0.880795
not succ 0.3 0.3 0.09 0.119205 0.119205
0.755
bad suc 0.7 0.05 0.035 0.142857 0.142857
not succ 0.3 0.7 0.21 0.857143 0.857143
0.245

payoffs in thousands 0.888889

recpt
400
without ad 0 400

0 377.7778 0.111111
non recpt
200
good 0 200
2
0 760.596 0.880795
succ
850
with ad 0 850

0 760.596 0.119205
not succ
100
0 100

#N/A 0.571429
recpt
400
without ad 0 400

0 314.2857 0.428571
non recpt
200
bad 0 200
1
0 314.2857 0.142857
succ
850
with ad 0 850

0 207.1429 0.857143
not succ
100
0 100
15 Company A has developed a new product and has to decide whether to launch the product in the market
on its own or sell-off the rights for Rupees 60 million. The company believes that there are 50-50 chances
that the market response to the product will be very good or just about average. If the response is very good
the company expects to earn Rupees 300 million, but if just about average then only Rupees 30 million (the
present value of the future operating profits.).These earning are exclusive of the cost of initial launch of
Rupees 75 million.

Prior to a decision on launch the company has the option of test marketing the product, at a cost of Rupees 8
million. The test may give a favorable response or an unfavorable response for the product. The conditional
probabilities of the market response under the true states of very good or just average market condition are
tabulated below:
Test outcome
True market state Unfavorable Favorable
Very good 0.1 0.9
Just average 0.7 0.3
Using a Decision Tree analysis, determine the optimal policy that the company should follow.
p(Fav &
Forecast Events p(Ei) p(fav/Ei) Ei) P(Ei/Fore)
Very
Fav Good 0.5 0.9 0.45 0.75
Average 0.5 0.3 0.15 0.25
1 0.6 1

Very
Fav Good 0.5 0.1 0.05 0.125
Average 0.5 0.7 0.35 0.875
1 0.4 1

Sell rights
60
0 60
do not test
2 0.5
0 90 Very good
225
Market self 0 225

0 90 0.5
Average
-45
0 -45

2 Sell rights
110.5 52
0.6 0 52
Fav
2 0.75
0 149.5 Very good
217
Market self 0 217

0 149.5 0.25
test market Average
-53
0 110.5 0 -53

Sell rights
52
0.4 0 52
Unfav
1 0.125
0 52 Very good
217
Market self 0 217

0 -19.25 0.875
Average
-53
0 -53
16. John Silver can use his boat, the Jolly Roger, for either commercial tuna fishing or sport fishing. For the
latter, he rents it our at a daily charge of $500. In a fishing season with good weather, he averages 150
rental days. However, if the weather is bad, he averages only 105 renal days. For each day the boat is
rented, John estimates he incurs variable costs of about $135. When the weather is good, the revenues
from fishing for tuna exceed the variable costs of that operation by $50,000, whereas in seasons with
bad weather, the profit contribution from tuna fishing is only $43,000. At the beginning of the 1997
season, John feels that the odds are about 7 to 3 in favor of good weather for the season.
(a) Use a decision tree to help John decide how to use the Jolly Roger during the 1997 fishing season.
(b) How much would John pay for a perfectly reliable long-range weather forecast for the season?
0.7
Good

Tuna 0 50

0 47.9 0.3
Bad

0 43
2
49.8225 0.7
Good

Sports 0 54.75

0 49.8225 0.3
Bad

0 38.325

John’s good friend, Jim Hawkins, runs a private weather forecasting service that has been 90 percent
accurate in the past. In 90 percent of all seasons that had good weather, Jim had forecast good weather,
and likewise in 90 percent of all seasons when the weather proved to be bad, Jim’s forecast had been for
bad weather. Jim usually sells his forecast for $1,000, but because John is a good friend, Jim is willing to
sell it to him for only $400.
(c) Expand your decision tree to help John decide whether he should buy Jim’s forecast. How will the
forecast affect his use of the boat during the 1997 seasons?
(d) Would John buy Jim’s forecast if they weren’t friends? Explain. What is the maximum amount John
would be willing to pay for the forecast?

P(Favour
Fore Ei P(Ei) P(Favour/Ei) &Ei) P(Ei/Favour)
Good good 0.7 0.9 0.63 0.954545
Bad 0.3 0.1 0.03 0.045455
1 P(Favour)= 0.66 1
P(Favour
Ei P(Ei) P(Favour/Ei) &Ei) P(Ei/Favour)
Bad good 0.7 0.1 0.07 0.205882
Bad 0.3 0.9 0.27 0.794118
1 P(Favour)= 0.34 1
 0.9545
Good
49.6
Tuna 0 49.6

0 49.2815 0.0455
Bad
0.66 42.6
Good 0 42.6
2
0 53.60266 0.9545
Good
54.35
Sports 0 54.35

0 53.60266 0.0455
Bad
37.925
0 37.925

50.3518 0.2059
Good
49.6
Tuna 0 49.6

0 44.0413 0.7941
Bad
0.34 42.6
Bad 0 42.6
1
0 44.0413 0.2059
Good
54.35
Sports 0 54.35

0 41.30691 0.7941
Bad
37.925
0 37.925
Ans : Without forecast = $49823 With forecast emv= $50352/- Maximum payment = $929
17. A company is considering merging with a smaller firm in a related industry. The company’s chief
executive officer believes that the merger has a 0.55 probability of success. If the merger is successful, the
company stands to gain in the next 2 years $ 5 million with probability 0.2; $6 million with probability of 0.3;
$7 million with probability 0.3; and $8 million with probability 0.2. If the attempted merger should fail, the
company stands to lose $2 million (due to loss of public goodwill) over the next 2 years with probability 0.5
and to lose $3 million over this period with probability 0.5. Should the merger be attempted? Explain.
0.2
Event 1
5
0 5

0.3
Event 2
0.55 6
S 0 6

0 6.5 0.3
Event 3
7
0 7

Merge 0.2
Event 4
0 2.45 8
0 8

0.5
Event 5
0.45 -2
Do not hire F 0 -2
1
2.45 0 -2.5 0.5
Event 6
-3
0 -3

Do not Merge
0
0 0
18. For problem 17, suppose that the chief executive officer may hire a consulting firm for a fee of $725,000.
The consulting firm will advise the CEO about the possibility of success of the merger. This consulting firm
is known to have correctly predicted the outcomes of 89% of all successful mergers and the outcomes of 97%
of all unsuccessful ones. What is the optimal decision?
0 5

0.3
Event 2
0.55 6
S 0 6

0 6.5 0.3
Event 3
7
0 7

Merge 0.2
Event 4
0 2.45 8
0 8

0.5
Event 5
0.45 -2
Do not hire F 0 -2
1
0 2.45 0 -2.5 0.5
Event 6
-3
0 -3

Do not Merge
0
0 0

0.2
Event 1
4.275
0 4.275

0.3
Event 2
0.973 5.275
S 0 5.275

0 5.775 0.3
Event 3
6.275
0 6.275

1 Merge 0.2
2.45 Event 4
0 5.532 7.275
0 7.275

0.5
Event 5
0.503 0.027 -2.725
Forecast says Success F 0 -2.725
1
0 5.532 0 -3.225 0.5
Event 6
-3.725
0 -3.725

Do not merge
-0.725
0 -0.725

0.2
Event 1
4.275
0 4.275

Hire 0.3
Event 2
0 2.422271 0.122 5.275
 0.2
Event 1
4.275
0 4.275

0.3
Event 2
0.973 5.275
S 0 5.275

0 5.775 0.3
Event 3
6.275
0 6.275

1 Merge 0.2
2.45 Event 4
0 5.532 7.275
0 7.275

0.5
Event 5
0.503 0.027 -2.725
Forecast says Success F 0 -2.725
1
0 5.532 0 -3.225 0.5
Event 6
-3.725
0 -3.725

Do not merge
-0.725
0 -0.725

0.2
Event 1
4.275
0 4.275

Hire 0.3
Event 2
0 2.422271 0.122 5.275
S 0 5.275

0 5.775 0.3
Event 3
6.275
0 6.275

Merge 0.2
Event 4
0 -2.127 7.275
0 7.275

0.5
Event 5
0.497 0.878 -2.725
Forecast says Failure F 0 -2.725
2
0 -0.725 0 -3.225 0.5
Event 6
-3.725
0 -3.725

Do not merge
-0.725
0 -0.725

p(Pred
Event p(ei) p(pred/Ei) & Ei) P(Ei/Pred)
S 0.55 0.89 0.4895 0.973161
F 0.45 0.03 0.0135 0.026839
1 0.503 1

S 0.55 0.11 0.0605 0.12173

F 0.45 0.97 0.4365 0.87827
1 0.497 1

19 A textile mill must decide whether to extend $ 150,000 credit to a new customer that manufacturers
dresses. The mill’s prior experience with a number of dress manufacturers has led it to classify such
customers as follows: 25 percent are poor risks, 45 percent are average risks, and 30 percent are good risks.
Expected profits on this order (if credit is extended to the dress manufacturer) are - $20,000 if it returns out to
be a poor risk, $18,000 if it turns out to be an average risk, and $25,000 if it turns out to be an good risk. Draw
a decision tree to determine whether the mill should extend credit to this manufacturer.

0.25
Poor
-20000
0 -20000

0.45
Give credit Average
18000
0 10600 0 18000

0.3
Good
1 25000
10600 0 25000

Do not give credit

0
0 0
For $750, the textile mill can purchase a comprehensive credit analysis and rating of the manufacturer. The
rating, in increasing order of creditworthiness, will be C, B, or A. The credit agency’s reliability is summed up
in the following table, whose entries are the probabilities (from past experience) of the agency’s rating of the
dress manufacturer, given the true credit category in which the manufacturer belongs.
True Category

Average Rating Poor Average Good

A 0.1 0.1 0.6

B 0.2 0.8 0.3
C 0.7 0.1 0.1
(a) Use Bayes’ Theorem and a decision tree to determine whether the mill should purchase the credit
rating.
(b) If it does purchase the rating, how will this affect the decision to grant credit to the dress
manufacturer?
(c) What is the maximum amount the mill will be willing to pay for the credit report?
Rating Event P(Ei) P(Rating/Ei) P(Rating &Ei) P(Ei/Rating)
A Poor 0.25 0.1 0.025 0.1
Average 0.45 0.1 0.045 0.18
Good 0.3 0.6 0.18 0.72
0.25 1
B Poor 0.25 0.2 0.05 0.1
Average 0.45 0.8 0.36 0.72
Good 0.3 0.3 0.09 0.18
0.5 1
C Poor 0.25 0.7 0.175 0.7
Average 0.45 0.1 0.045 0.18
Good 0.3 0.1 0.03 0.12
0.25 1
The maximum amount the mill is ready to pay is 750+ (11790 – 10600 ) = 1940
 0.1
Poor
-20750
0 -20750

0.18
Give Credit Average
17250
0 18490 0 17250

0.25 0.72
A Good
1 24250
0 18490 0 24250

Do not give credit

-750
0 -750

0.1
Poor
-20750
0 -20750

0.72
Give Credit Average
17250
0 14710 0 17250

0.5 0.18
Buy B Good
1 24250
0 11790 0 14710 0 24250

Do not give credit

-750
0 -750

0.7
Poor
-20750
0 -20750

0.18
Give Credit Average
17250
0 -8510 0 17250

0.25 0.12
C Good
1 2 24250
11790 0 -750 0 24250

Do not give credit

-750
0 -750

0.25
Poor
-20000
0 -20000

0.45
Give Credit Average
18000
0 10600 0 18000

0.3
Do not buy Good
1 25000
0 10600 0 25000

20 Christie Stem, the owner and general manager of the Snow Fun Ski Resort, decide how the hotel should
be run in the coming season. Christie’s profits for this year’s skiing season will depend on how much snowfall
occurs during the winter. On the basis of previous experience, she believes the probability distribution of
snowfall and the resulting profit can be summarized as
Table Amount of Snow Profit Probability of
Occurrence
Distribution of More than 40 $120,000 0.4
Snowfall and Profit inches
for Snow Fun Ski 20 to 40 inches 40,000 0.2
Resort Less than 20 inches - 40,000 0.4
Christie has recently received an offer from a large hotel chain to operate the resort for the winter,
guaranteeing her a $ 45,000 profit for the season. She has also been considering leasing snowmaking
equipment for the season. If the equipment is leased, the resort will be able to operate full time, regardless of
the amount of natural snowfall. If she decides to use snowmakers to supplement the natural snowfall, her
profit for the season will be $120,000 minus the cost of leasing and operating the snowmaking equipment.
The leasing cost will be about $12,000 per season, regardless of how much it is used. The operating cost will
be $10,000 if the natural snowfall is more than 40 inches, $50,000 if it is between 20 and 40 inches, and
$90,000 if it is less than 20 inches.

Let Hotel Operate

45
0 45

0.4
>40"
120
0 120

0.2
Operate by self without SM 20 - 40 "
40
0 40 0 40
3
58 0.4
< 20 "
-40
0 -40

0.4
>40"
98
0 98

0.2
Operate by self with SM 20 - 40 "
58
0 58 0 58

0.4
< 20 "
18
0 18
Just as Christie is getting ready to decide whether to let the hotel chain operate Snow Fun or to operate
it herself, she receives a call from Meteorological Associates offering to sell her a forecast of snowfall in the
coming season. The price of the forecast will be $2,000. The forecast will indicate either that the snowfall will
be above normal or else that it will be below normal. After doing a bit of research, Christie learns that
Meteorological Associates is a reputable firm whose forecasts have been quite good in the past, although, of
course, they haven’t been perfectly reliable. In the past, the firm has forecast above normal snowfall in 90
percent of all years when the natural snowfall has been above 40 inches, in 60 percent of all years when it has
been between 20 and 40 inches, and in 30 percent of the years in which it has been below 20 inches.
 0.6
>40"
118
0 118

0.2
Operate by self without SM 20 - 40"
38
0 70 0 38

0.2
< 20"
-42
0 -42

0.6
>40"
0.6 96
Fav 0 96
2
0 72 0.2
Operate by self with SM 20 - 40"
56
0 72 0 56

0.2
< 20"
16
0 16

Let Hotel Operate

43
0 43

Forecast 0.1
>40"
0 60.4 118
0 118

0.2
Operate by self without SM 20 - 40"
38
0 -10 0 38

0.7
< 20"
-42
0 -42

0.1
>40"
0.4 96
Not Fav 0 96
3
0 43 0.2
Operate by self with SM 20 - 40"
56
0 32 0 56

0.7
< 20"
1 16
60.4 0 16

Let Hotel Operate

43
0 43

0.4
>40"
120
0 120

p(fore &
Forecast Event p(Ei) p(fore/Ei) Ei) P(Ei/fore)
>40" 0.4 0.9 0.36 0.6
Above
normal 20 - 40 " 0.2 0.6 0.12 0.2
< 20" 0.4 0.3 0.12 0.2
0.6 1

Below
Normal >40" 0.4 0.1 0.04 0.1
20 - 40 " 0.2 0.4 0.08 0.2
< 20" 0.4 0.7 0.28 0.7
0.4 1

21. 16. MBI Corporation manufactures computers. Its product line includes a personal computer whose sales
currently represent a 20% share of the total market. (For simplicity, we will assume that only three market
shares are possible: 10%, 20% and 30%.) MBI believes that its current 20% market share is likely to fall
dramatically unless it can introduce an improved model in about a year. Consequently, MBI must now select
one of the following options:

(1) Keep selling the current model without making any improvements. If this is done, MBI estimates its
market share will either remain at 20% with probability 0.4 or fall to 10% with probability 0.6. MBI also
estimates that the present value of future sales of an unimproved model is Rs1.5 million per percent of
market share (e.g. a 20% market share has a value of 1.5 x 20 = 30 million)
(2) Develop a model with one (but not both) of two types of improvements – hereafter referred to as
improvement A and improvement B. Research and development costs are Rs20 million for improvement
A and Rs 25 million for improvement B. Each type of improvement will result in either a significant or a
slight improvement. For improvement A, MBI believes the probability of significant improvement is 0.8,
and of slight improvement is 0.2. For improvement B, the probability of significant improvement is 0.5,
and of slight improvement is 0.5. MBI estimates that the present value of future sales for a significantly
improved model is Rs3 million per percent of market share and for a slightly improved model is Rs2
million per percent of market share.

If MBI chooses to begin development of either type of improvement, it will subsequently face another
decision. After learning whether its research and development has led to a significantly improved or slightly
improved model, MBI must then decide whether to launch (i.e. begin selling) the improved model or to keep
selling the current model. If MBI decides to launch an improved model, it will incur additional costs of Rs15
million, regardless of whether the improvement has been significant or slight. With an improved model, MBI
estimates that the respective probabilities of market shares of 10%, 20%, and 30% are:

 0.2, 0.4 and 0.4 if the model is a significant improvement of type A

 0.5, 0.4 and 0.1 if the model is a slight improvement of type A
 0.0, 0.2 and 0.8 if the model is a significant improvement of type B
 0.2, 0.5 and 0.3 if the model is a slight improvement of type B

What is the optimal strategy for MBI under the EMV criterion?
 0.4
twenty
30
Decision 1 0 30

0 21 0.6
ten
15
0 15

0.2
t en
-5
0 -5

0.4
launch t wenty
25
0 31 0 25

0.4
0.8 t hirty
signif icant 55
1 0 55
0 31
0.4
t wenty
10
do not launch 0 10

0 1 0.6
t en
-5
0 -5
Decision 2
0.5
0 25 t en
-15
0 -15

0.4
launch t wenty
5
0 -3 0 5
2
25 0.1
0.2 t hirty
slight 25
2 0 25
0 1
0.4
t wenty
10
do not launch 0 10

0 1 0.6
t en
-5
0 -5

0
t en
-10
0 -10

0.2
launch t wenty
20
0 44 0 20

0.8
0.5 t hirty
signif icant 50
1 0 50
0 44
0.4
t wenty
5
do not launch 0 5

0 -4 0.6
t en
-10
0 -10
Decision 3
0.2
0 23 t en
-20
0 -20

0.5
launch t wenty
0
0 2 0 0

0.3
0.5 t hirty
slight 20
1 0 20
0 2
0.4
t wenty
5
do not launch 0 5

0 -4 0.6
t en
-10
0 -10
23 A company is trying to decide whether to bid for a certain contract or not. They estimate that merely
preparing the bid will cost Rs 8,00,000/-. If their company bid then they estimate that there is a 50% chance
that their bid will be put on the "short-list", otherwise their bid will be rejected.Once "short-listed" the
company will have to supply further detailed information (entailing costs estimated at Rs 4Lks). After this
stage their bid will either be accepted or rejected.
The company estimate that the labour and material costs associated with the contract are Rs 100 Crores. They
are considering three possible bid prices, namely Rs 119 Crs,Rs 136 Crsand Rs£153 Crs. They estimate that
the probability of these bids being accepted (once they have been short-listed) is 0.90, 0.75 and 0.35
respectively.
What should the company do and what is the expected monetary value of your suggested course of action?

do nothing
0
0 0

0.5
fail to shortlist
-8
0 -8
2
1340 0.9
Accepted
1888
bid for 119 cr 0 1888

0 1698 0.1
prepare bid Rejected
-12
0 1340 0 -12

0.75
accepted
3588
bid for 136 cr 0 3588

0 2688 0.25
0.5 rejected
shortlist -12
2 0 -12
0 2688
0.35
accepted
5288
bid for 153 cr 0 5288

0 1843 0.65
rejected
-12
0 -12

abandon
-8
0 -8