Scribd
Upload
7 views

Decision Tree

Uploaded by

Gulshan Kumar
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
7 views

Decision Tree

Uploaded by

Gulshan Kumar
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 12

PRESENTATION ON DECISION TREE (BY PROF.

VIJAY
PATIL)

Decision tree refers to decision making in situation that


involve multiple stages. They are characterized by a
sequence of decisions with each decision influencing the
next. Such problems called sequential decision problems
are analyzed best with the help of decision tree.
It consist of a network of nodes and branches .

Decision nodes : represented by square

Chance nodes : represented by circle

1
ROLL BACK OR FOLD BACK PROCESS

The general approach used in decision tree analysis is to


work backward through the tree from right to left
computing the expected value ( also called position
value) of each chance node. We then choose the
particular branch leaving a decision node which leads to
the chance node with the highest expected value. This is
known as roll back or fold back process.

2
QUESTION

• Mr. sinha had to decide whether or not to drill a well on


his firm .In his village only 40% of the well drilled were
successful at 200 feet of depth. Some of the formers
who did not get water at 200 feet drilled further up to
250 feet but only 20% struck water at 250 feet Cost of
drilling is rs 50 /feet . Mr sinha estimated that he would
pay 18000/- during a 5 years period in the present value
term if he continues to buy water from the neighbor
rather than go for the well which would have a life of 5
years. Mr. sinha has three decision to make :-

3
CONTINUE………

• Should he drill up to 200 feet


• If no water is found at 200 feet should be drilled up to
250 feet.
• Should he continue to buy water from his neighbor.

4
DECISION TREE

Water
Water struck
struck 0.2
Drill up 0.4 Drill up
to 200 to 250 B
A
1
No 2 No
water water
struck struck
Don’t Don’t 0.8
0.6
drill drill
5
CALCULATION OF EMV (EXPECTED MONETARY VALUE)

EMV of node B = ( 0.2*12500 + 0.8 * 30500) = 26900/-

EMV of node 2 = 26900 ( lesser of two values of 26900/

and 28000/- )

6
CALCULATION OF EMV (EXPECTED MONETARY VALUE)

• EMV on node A = ( 0.4*10000+0.6*26900)= 20140/-

• EMV on node 1 = 18000/- ( Lesser of the two values of

20140/- and 18000/-)

7
DECISION TREE ANALYSIS TABLE

Decision node Options Expected cost Decision

Drill up to 250 feet 26900/- Drill up to 250 feet

2
Stop 28000/-
(After 200 feet)
Drill up to 200 feet 20140/- Don’t Drill

1
Don’t Drill 18000/-

8
CONCLUSION

• Thus the optimal course of action for Mr. Sinha is not to


drill the well and pay Rs 18000/- for water to his
neighbor for five years.

9
QUESTION ANSWER SESSION

10
QUESTION

• If Mr sinha will have to pay 30000/- for buying the water


for 5 years duration in previous Question then Decision
would be ?
a) EMV on node B = (0.2*12500+ 42500*0.8) = 36500/-
b) EMV on node 2 = 36500/- ( Lesser of two value 36500/-
and 40000)
c) EMV on node A = (0.4* 10000+0.6*36500) = 25900/-
d) EMV on node 1 = 25900/- ( Lesser of two value 25900/-
and 30000/-)

11
CONCLUSION

• Thus the optimal strategy is to drill up to 200 feet and if


water is not struck then drill further to 250 feet.

12

You might also like