Quantitative Decision Making
Week 1
What makes a decision di cult?
-A lot of options
-Contradicting objectives
-Uncertainty about the outcome
A good decision:
-Criteria to evaluate the outcome
-Criteria to evaluate the process
Outcome bias= a bias in which people evaluate the quality of a decision solely based on
the outcome.
Basic inventory decision: costs of ‘too much’ vs. costs of ‘too little’.
Example Airline
Possible decisions:
-1 ight (200)
-2 ights (400)
Potential future scenarios:
Demand= 100, 200, 300, 400
Parameters:
-Cost per seat= €100
-Ticketprice= €200
-Penalty lost sales= €80
How many seats will we sell when we have a capacity of 200 and a demand of 300?
Sales= MIN(Capacity, Demand)= 200
How much is the out-of-stock penalty when the demand is 100 and the capacity is 200?
Out-of-stock penalty= MAX(Demand-Capacity, 0)= 0
Three types of decisions
1. Type 1 (under certainty)= the decision maker knows with certainty the consequences
of each decision.
2. Type 2 (under uncertainty)= the decision maker knows nothing about the probability of
each possible outcome.
3. Type 3 (under risk)= the decision maker knows the
probability distribution of the di erent outcomes.
Decision Criteria (under uncertainty)
MaxiMax Criterion (best-case)= for each decision, select the
best outcome.
MaxiMin Criterion (worst-case)= determine the worst
outcome and select the best outcome.
fl ffi ff
, Hurwicz Criterion
Select coe cient a between 0 and 1
1= 100% optimistic
0= 100% pessimistic
Weighted average= a x (best scenarios) + (1-a) x (worst scenario)
Calculate the weighted average for each alternative and select the alternative with the
highest value.
Hurwicz criterion (a=0.8)
200: 0.8 x 20 + 0.2 x 0= 16
400: 0.8 x 40 + 0.2 x -20= 28 <—
Laplace Criterion (equally likely)
For each alternative, determine the average outcome and select the best alternative.
MiniMax Regret
“Opportunity loss” or “regret”= the di erence between the actual outcome and the
maximum possible outcome. Select the alternative with the lowest regret.
Decision Criteria (under risk)
Expected Monetary Value (EMV)= weighted average of the
expected pro t.
ffi fi ff
Week 1
What makes a decision di cult?
-A lot of options
-Contradicting objectives
-Uncertainty about the outcome
A good decision:
-Criteria to evaluate the outcome
-Criteria to evaluate the process
Outcome bias= a bias in which people evaluate the quality of a decision solely based on
the outcome.
Basic inventory decision: costs of ‘too much’ vs. costs of ‘too little’.
Example Airline
Possible decisions:
-1 ight (200)
-2 ights (400)
Potential future scenarios:
Demand= 100, 200, 300, 400
Parameters:
-Cost per seat= €100
-Ticketprice= €200
-Penalty lost sales= €80
How many seats will we sell when we have a capacity of 200 and a demand of 300?
Sales= MIN(Capacity, Demand)= 200
How much is the out-of-stock penalty when the demand is 100 and the capacity is 200?
Out-of-stock penalty= MAX(Demand-Capacity, 0)= 0
Three types of decisions
1. Type 1 (under certainty)= the decision maker knows with certainty the consequences
of each decision.
2. Type 2 (under uncertainty)= the decision maker knows nothing about the probability of
each possible outcome.
3. Type 3 (under risk)= the decision maker knows the
probability distribution of the di erent outcomes.
Decision Criteria (under uncertainty)
MaxiMax Criterion (best-case)= for each decision, select the
best outcome.
MaxiMin Criterion (worst-case)= determine the worst
outcome and select the best outcome.
fl ffi ff
, Hurwicz Criterion
Select coe cient a between 0 and 1
1= 100% optimistic
0= 100% pessimistic
Weighted average= a x (best scenarios) + (1-a) x (worst scenario)
Calculate the weighted average for each alternative and select the alternative with the
highest value.
Hurwicz criterion (a=0.8)
200: 0.8 x 20 + 0.2 x 0= 16
400: 0.8 x 40 + 0.2 x -20= 28 <—
Laplace Criterion (equally likely)
For each alternative, determine the average outcome and select the best alternative.
MiniMax Regret
“Opportunity loss” or “regret”= the di erence between the actual outcome and the
maximum possible outcome. Select the alternative with the lowest regret.
Decision Criteria (under risk)
Expected Monetary Value (EMV)= weighted average of the
expected pro t.
ffi fi ff
