MBA666 - Decision - Trees Examples PDF
MBA666 - Decision - Trees Examples PDF
MBA666 - Decision - Trees Examples PDF
Remember the decision points, also called decision forks, denoted by D, and the alternative actions
are available for experimentation and actions are possible at these points, while the chance points,
called chance forks, denoted by C, are the points where the outcomes are dependent on a chance
process and the likely outcomes at these points.
Example # 1
The scientists at Spectrum have come up with an electric moped. The firm is ready for pilot
production and test marketing. This will cost Rs. 20 million and take six months. Management
believes that there is a 70% chance that the pilot production and test marketing will be successful. In
the case of success, Spectrum can build a plant costing Rs. 150 million. The plant will generate an
annual cash inflow of Rs. 30 million for 20 years if the demand is high or an annual cash inflow of Rs.
20 million if the demand is low. High demand has a probability of 0.6, while the probability of low
demand is 0.4. What is the optimal course of action using decision tree analysis.
1
MBA666: Project Management
Raghu Nandan SENGUPTA, IME Dept., IIT Kanpur, INDIA
Solution # 1
C21; P(C21=0.6)
(30 million per year)
D3
Stages of evaluation
At C2
EMV (C2 ) = 0.630 *
1 1 1
+ + + ; EMV : Expected Monetary Value
(1 + 0.12) (1 + 0.12) (1 + 0.12)20
1 2
1 1 1
+ 0.420 * + ++ 20
(1 + 0.12) (1 + 0.12) (1 + 0.12)
1 2
At D2
D21 = EMV(D21) = 194.2-150=44.2
D22 = EMV(D22)= 0
As D21 > D22, hence D21 is selected
At C1
EMV(C1)=0.7*44.2+0.3*0=30.9
At D1
2
MBA666: Project Management
Raghu Nandan SENGUPTA, IME Dept., IIT Kanpur, INDIA
D11 = EMV(D11)=30.9-20.0=10.9
D12 = EMV(D12)=0
As D11 > D12, hence D11 is selected
Example # 2
An oil company while evaluating the oil basin is considering three alternatives, which are (i) drill, (ii)
conduct seismic test before at a cost of Rs. 20000 to find the nature of the underlying oil basin and
(iii) do nothing. If the company drills then it is likely to find the oil basin as (i) dry, (ii) wet or (iii)
soaking. A dry well yields nothing, while a wet well provides moderate quantity of oil and a soaking
well generates substantial quantity of oil. If the oil company conducts seismic tests, then it can learn
about the underlying structure of the oil basin before deciding whether to drill for oil or not. The
underlying oil basin structure may be one of the following, which are (i) no structure, (ii) open
structure or (iii) closed structure. If no structure is found then the prospect of finding oil is bleak. If an
open structure is discovered then the prospect of finding oil is fair, while finally if the structure is
closed then the prospect of finding oil is bright.
The oil company also knows the following which are
Also we have the following joint probability distribution between underlying geological structure and
oil bearing state.
3
MBA666: Project Management
Raghu Nandan SENGUPTA, IME Dept., IIT Kanpur, INDIA
Oil bearing
state
Marginal probability of the 0.40 0.30 0.30 1.00
geological structure
Finally the oil company also has the following set of information regarding the net present value of
the three states, which are: (i) NPV(Dry state)=-0 6 million;(ii) NPV(Wet state)=0.8 million and (iii)
NPV(Soaking state)=2.4 million
Solution # 2
At C1
At C3
At C4
4
MBA666: Project Management
Raghu Nandan SENGUPTA, IME Dept., IIT Kanpur, INDIA
Dry
C11; P(C11=1/2) 0.6
Wet
D11 (Drill) C12; P(C12=1/4) 0.8
Soaking
C13; P(C13=1/4) 2.4
D11 Dry
(Drill) C31; P(C31=4/5) 0.6
Wet
D21 (Drill) C32; P(C32=1/10) 0.8
Soaking
D2 C33; P(C33=1/10) 2.4
D22
C21 (Do not drill) Dry
P(C21=4/10) C41; P(C41=1/2) 0.6
(No structure) D31 Wet
(Drill) C42; P(C42=1/3) 0.8
D12 C22 Soaking
D1 Conduct D3 C43; P(C43=1/6) 2.4
Test P(C22=3/10) D32 Dry
0.02 (Do not drill) C51; P(C51=1/10)
C23 D41 Wet 0.6
P(C23=3/10) (Drill) C52; P(C52=11/30)
(Closed Structure) Soaking 0.8
D4
C53; P(C53=16/30)
D42 2.4
(Do not drill)
C22
(Open Structure)
D13
Do
Nothing Stages of evaluation
D13
At C5
5
MBA666: Project Management
Raghu Nandan SENGUPTA, IME Dept., IIT Kanpur, INDIA
At C2
EMV (C2 ) = 0.4 * 0 + 0.3 * 3.67 + 0.3 *1.513 = 0.564
Based on the above evaluation of alternatives we can find that the set of decision strategies as follows,
from which we choose the optimal decision strategy
So:
E(NPV)= (− 20000 )* 0.4 + (− 620000 ) * 0.15 + (780000 ) * 0.10 + (2380000 ) * 0.05
6
MBA666: Project Management
Raghu Nandan SENGUPTA, IME Dept., IIT Kanpur, INDIA
1
+ (780000− 544000) * 0.11 + (2380000− 544000) * 0.16}2
2 2
We can make our decision accordingly as one may want to (i) maximize return or (ii) minimize risk or
(iii) make a balance between them, i.e., max{return/risk} or min{risk/return}.
7
MBA666: Project Management
Raghu Nandan SENGUPTA, IME Dept., IIT Kanpur, INDIA
Dry
C11; P(C11=1/2) 0.6
Wet
D11 (Drill) C12; P(C12=1/4) 0.8
Soaking
C13; P(C13=1/4) 2.4
D11 Dry
(Drill) C31; P(C31=4/5) 0.6
Wet
D21 (Drill) C32; P(C32=1/10) 0.8
Soaking
D2 C33; P(C33=1/10) 2.4
D22
C21 (Do not drill) Dry
P(C21=4/10) C41; P(C41=1/2) 0.6
(No structure) D31 Wet
(Drill) C42; P(C42=1/3) 0.8
D12 C22 Soaking
D1 Conduct D3 C43; P(C43=1/6) 2.4
Test P(C22=3/10) D32 Dry
0.02 (Do not drill) C51; P(C51=1/10)
C23 D41 Wet 0.6
P(C23=3/10) (Drill) C52; P(C52=11/30)
(Closed Structure) Soaking 0.8
D4
C53; P(C53=16/30)
D42 2.4
(Do not drill)
C22
(Open Structure)
D13
Do
Nothing
D13
8
MBA666: Project Management
Raghu Nandan SENGUPTA, IME Dept., IIT Kanpur, INDIA
where
rk = risk adjusted discounted rate for the kth project
rf = risk free rate of interest
n = adjustment for the firms notional risk
dk = adjustment for the differential risk for the kth project
Hence
T Aˆk ,t
NPVk = t
− Ik
t =1 (1 + rk )
where
Aˆ k , t = Expected or estimated cash flow for the kth project at the tth time period
T Aˆ
NPVk = k ,t k ,tt − I k
t =1 (1 + rf )
where
Aˆ k , t = Expected or estimated cash flow for the kth project at the tth time period
9
MBA666: Project Management
Raghu Nandan SENGUPTA, IME Dept., IIT Kanpur, INDIA
If
k,t = 1, then the person is risk indifferent
k,t < 1, then the person is risk avoider
k,t > 1, then the person is risk indifferent
Certainty index
In general we may term it as the probability of being positive, i.e., if we say the certainty index of
procuring raw materials on time is 85%, then it means that the probability that the raw materials are
obtained in tie are 85%
In evaluation remember that if there are three stages for the completion of the project such that we can
have A leads to B then to C and then D or A to C then to B and then to D, then the corresponding
probability would be calculated utilizing
P(A)*P(B|A)*P(C|A and B)*P(D|A, B and C) and
P(A)*P(C|A)*P(B|A and C)*P(D|A, C and B)
10