1 Term Project MBA 550 Decision Support Systems
Jun 20, 2015
11
Term Project
MBA 550
Decision Support Systems
Term Project
MBA 550
Decision Support Systems
Introduction
People make decisions all the time. Sometimes we choose to do things without even knowing why we did it. In business, however, decisions have to be well calculated as this determines whether the business will survive. Decision-making models are a structured way of making decisions. A decision-making situation includes several components-the decision themselves and the actual events that may occur in the future. At the time a decision is made, the decision maker is uncertain which states of nature will occur in the future and has no control over them.
Introduction (cont.)
Several decision-making techniques are available to aid the decision maker in dealing with this type of decision situation in which there is certainty or uncertainty.
Decision situation can be categorized into two classes: a. Situations in which probabilities cannot be
assigned to future occurrences.b. Situations in which probabilities can be
assigned.
This project is about Decision-Making Models. First we will explain the problems, provide solutions , and evaluate the project.
MBA 550 Team Project
PROBLEM #1PROBABILITY FOR EACH ECONOMIC CONDITIONS (GOOD AND BAD)(situations in which probabilities cannot be assigned to future occurrences)
PROBLEM#2EXPECTED VALUE OF PERFECT INFORMATION AND DETERMINE THE BEST PROJECT(situations in which probabilities can be assigned)
Problem # 1
An investor must decide between two alternative investments-stocks and bonds. The return for each investment, given two future economic conditions, is shown in the following payoff table:
____________________________________ Economic ConditionsInvestments Good BadStocks $10,000 $-4,000
Bonds 7,000 2,000
What probability for each economic condition would make the investor indifferent to the choice between stocks and bonds?
Answer
To make investor indifference:Let x1 = good probability and x2 = bad probability
The probabilities are unknown, but you want the expected values of choosing either stocks or bonds to be the same, then:
(10000)x1 + (-4000)x2 = (7000)x1 + (2000)x2And where x1 + x2 = 1, or x2 = 1 – x1
Stocks = bonds
Answer (cont.)
Substituting for x2 = (1 – x1)
(10000)x1 + [(-4000)(1 – x1)] = (7000)x1 + [(2000)(1-x1)]
Multiplying this out:(10000)x1 – 4000 + (4000)x1 = (7000)x1 + 2000- 2000x1
Combining whole numbers and multiples of x1
(9)x1 = 6Then x1=6/9 = .67 (there is rounding in this fraction; rounding fractional solutions will results in suboptimal solutions (not the optimal solutions).
Answer (cont.)
x1 = good conditions probability = .67X2 = bad conditions probability = (1-x1) = (1-.67) = .33
.67 ($10000) + .33 ($-4000) = .67 ($7000) = (1- .67) = .33
Notice due to “rounding off” to the nearest conditions probabilities, the solutions resulted in suboptimal not optimal solutions.
Stocks 6700 + (-1320) = 5380Bonds 4690 +e 660 = 5350
Problem # 2
DEFENSE
Play 54 63Wide
Tackle Nickel Blitz
Off tackle 3 -2 9 7 -1
Option -1 8 -2 9 12
Toss sweep 6 16 -5 3 14
Draw -2 4 3 10 -3
Pass 8 20 12 -7 -8
Screen -5 -2 8 3 16
Problem # 2 (cont.)
Answer
DEFENSE
54 63Wide
Tackle Nickel Blitzprobability
(a) 0.4 0.1 0.2 0.2 0.1Off Tackle 3 -2 9 7 -1Option -1 8 -2 9 12Toss Sweep 6 16 -5 3 14Draw -2 4 3 10 -3Pass 8 20 12 -7 -8Screen -5 -2 8 3 16
probablility
(b) 0.1 0.1 0.1 0.1 0.6
Answer (cont.)
weighted yds/play a) best to worst ranking
4.1 pass 1 5.43 toss sweep 2 55 off tackle 3 4.1
1.9 option 4 35.4 draw 5 1.91.6 screen 6 1.6
1.1 b) Toss sweep 8.6
10.4-0.3-1.510
Evaluation
In this term project, we examined and learned two decision models. Problem number one is a situationin which an investor needs to decide between two alternative investments- stock and bonds. This is a situation in which probabilities cannot be assigned to future occurrences. We don’t know what’s the economic conditions is going to be. It’s either good or bad economic conditions. Since the probabilities are unknown, we want the expected values of choosing either stocks or bonds to be the same. In real situations, however, model parameters are frequently uncertain because they reflect the future as well as the present, and future conditions are rarely known with certainty. We also found out that “rounding off” fractions can result in a suboptimal solutions.
Evaluation (cont.)
In problem number two, we apply the concept of expected value as a decision-making criterions. We first estimate the probability of occurrence of each state of nature. Once the estimate have been determined, the expected value for each decision alternative can be computed. In our problem, the Tech has the game data of the State, and reviewed the probabilities that State will use each of its defense. Tech coaches was able to determined what play should they run, if they have the third down and has 10 yards away from the goal line.
References
Taylor, B. (2010) Introduction to Management Science, New Jersey. Prentice Hall