A decision tree can be used instead of a table to show alternatives, outcomes, and payoffs.

Trees are
much more powerful than tables, which are limited to two dimensions, e.g alternatives and outcomes.

 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, from which one of several alternatives may be chosen.
 All decision trees contain state-of-nature points or nodes, out of which one state of nature will
occur.

Five Steps of Decision Tree Analysis

1. Define the problem.
2. Structure or draw the decision tree.
3. Assign probabilities to the states of nature.
4. 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.
Structure of Decision Trees
 Trees start from left to right.
 Trees 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.
A decision tree consists of nodes and arcs:

Represents a Decision Node

Represents an outcome node

(Arcs/Lines) indicates decision alternatives or outcomes (States of nature)

A decision tree shows the order of decisions and outcomes.

The ABD Manufacturing company must decide whether to manufacture a component part at its Chennai
Plant or Purchase the component part from the supplier. The resulting profit is dependent upon the
demand for the product.

The following payoff table shows the projected profit:

Decision Alternatives State of Nature

 Low Demand Medium Demand High Demand

Manufacture -20,000 40,000 1,00,000

Purchase 10,000 45,000 70,000

Show the order of decisions and outcomes using a decision tree.

-20,000
em and
Low D
Medium Demand
-40,000
High Demand
H -1,00,000

d
De man -10,000
Low
Medium Demand 45,000
High Demand
70,000

A Process of identifying the optimal decision in a decision tree

The process begins after a complete decision tree has been developed

Moving from right to left, Calculate the expected payoff at each outcome node.]

At Each decision node, select the best decision alternative (Based on Expected payoff calculated at each
outcome node):

Largest payoff for the maximization problem, or

Lowest cost for the minimization problem

Example 2:

Extending from Example 1, suppose that the state of nature probabilities are ( Low Demand) =
0.35, P(Medium Demand) = 0.35 and P(High Demand)- 0.3. Calculate the expected payoff at each
outcome node and identify the best decision alternative based on the expected payoff.

Solution:
Expected payoff for a manufacture component is

Low Demand

Medium Demand
2
High Demand

EMV( Node 2) = ( 0.35 X (-20,000)) + (0.35 X 40,000) + (0.3 X 1,00,000))

= 37,000 Low Demand

Expected payoff to purchase Component Medium Demand

2
High Demand

EMV( Node 3) = (0.35 X 10,000) +(0.35 X 45,000) + (0.3 X 70,000)

= 40,250

Therefore, the best decision alternative would be to purchase the component since it yields the largest
expected payoff rs 40,250

Problem

Monica is considering the possibility of starting a company to produce small sailboars.

With favorable market, Monica expects to make

90.000 from a large facility or

60,000 from a smaller facility

If the market is unfavorable, Monica estimates that she would loose

30,000 a large facility or

20,000 with a small facility

She can also decide not to pursue her business idea.

She estimates the probability of a successful market is 60%

Use a decision tree to give a recommendation

EMV(Node 1) = Max ( EMV(Node 2), EMV(node 3), EMV(node 4))

= Max (42,000, 28,000)

= 42,000

Therefore, Monica should start a company using a large facility to produce the sailboats.

ABC Toys Pvt Ltd is considering the addition of a new toy to its existing product line. Three alternative
courses of action are available:

a) Work overtime to meet the demand of the new toy. Overtime expenses are estimated at
Rs.20.000 per month.
b) Install new equipment which fixed expenses per month are expected at Rs. 80,000.
c) Lease (rent) a machine at the rate of Rs. 35,000 per month.

Variable cost associated with the above three alternatives are Rs. 9, Rs.7, Rs.8 per toy respectively. The
price per unit of the toy, which is independent of the manufacturing alternative, is fixed at Rs. 15. The
Expected demand for the toy is as given below:

10,000 pieces with a probability of 0.5

20,000 pieces with a probability of 0.3

50,000 pieces with a probability of 0.2

Which alternative should the company adopt to manufacture the toy?

Solution:

A pharmaceutical firm is planning to develop and market a new drug. The cost of
extensive research to develop the drug has been estimated at Rs.1,00,000. The manager
has found that there is a 60% chance that the drug would be developed successfully. The
market potential is as given below:
Market Condition (Potential) Probability Present Value PV (profit)

Large 0.1 50,000

Moderate 0.6 25,000

Low 0.3 10,000

P.V. figures do not include the cost of research. While the firm is considering this
proposal, a second proposal almost similar comes up for consideration. The second one
also requires an investment of Rs.100000 but P.V. of all profits is 12,000. ROI in second
proposal is certain.
(a) Draw a decision tree indicating all events and choices of the firm.
(b) What decision must the firm take regarding the investment of Rs. 100000?
SOLUTION
Decision trees are easy to construct just by using pure logic. Based on the given

information we know that the firm has two proposals. These are shown in the first branching.

In case the pharmaceutical firm decides to develop the drug, there is a 60% probability that the
project would be successful and there is a 40% probability that it might fail. If the

development of the drug is successful, then there is a 10% probability of a large market

potential, 60% of a moderate market potential and 30% of a low market potential. The

possible returns in rupees associated with the market potential is also shown in the diagram.

The computations of the Returns on Investment (ROI) are shown below the diagram. We

find that it would benefit the firm to go ahead and develop the drug instead of accepting

the second proposal as the development of the new drug despite the possibility of being

unsuccessful still yields are probable higher return.

ROI for 1-----st proposal =(50000*0.1*0.6) + (25000*0.6*0.6) + (10000*0.3*0.6)

= Rs. 13800

ROI for 2nd proposal = Rs. 12000

The 1-----st proposal to develop and market drugs gives better returns.

We have two similar situations illustrated in example 4.3.2 and 4.3.3. I would suggest

that you read the question then try to draw the decision tree on your own and then verify

the solution.

Example 4.3.2:
You have an option to invest Rs.10000 in the stock market by buying shares of
company A or B. Shares of company A are risky but could yield 50% ROI during the next

year. If the stock market conditions are not favorable, the stock will lose 20% of its value.

Company B provides soft investments with 15% returns in bullish market and only 5% in a
Bearish market. All stock market journals predict 60% chance for a Bull market. In

which company would you invest?

Solution:

5000

Bear A -2000

D
1500
B
Bull 500

For A,
E.V.= 5000(0.6)+(-2000)(0.4)
=3000-800 = Rs.2200.
For B,
E.V.=1500(0.6)+500(0.4)
=900+200 = Rs.1100.
So, A is better. Since A gives higher ROI, we will invest on A.