Scribd
Upload
95 views

Multiple Attribute Decision Making

The document discusses several scoring methods and multi-attribute decision making techniques, including the Simple Additive Weighting (SAW) method, Weighted Product method, TOPSIS, and ELECTRE. SAW scores alternatives based on a weighted sum of attribute values. Weighted Product transforms attributes using weights and multiplication. TOPSIS ranks alternatives based on their distance from the ideal positive and negative solutions. ELECTRE performs pairwise comparisons of alternatives to determine outranking relationships.

Uploaded by

lkouajiep
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
95 views

Multiple Attribute Decision Making

The document discusses several scoring methods and multi-attribute decision making techniques, including the Simple Additive Weighting (SAW) method, Weighted Product method, TOPSIS, and ELECTRE. SAW scores alternatives based on a weighted sum of attribute values. Weighted Product transforms attributes using weights and multiplication. TOPSIS ranks alternatives based on their distance from the ideal positive and negative solutions. ELECTRE performs pairwise comparisons of alternatives to determine outranking relationships.

Uploaded by

lkouajiep
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 7

SCORING METHODS

Management Science Multiple Attribute Decision Making By Dr. Apichat Sopadang

Scoring Methods
Transformation of a vector to an appropriate scalar value Formulate an index to represent its effectiveness => wind-chill factor, graduate school admission index Two scoring techniques: The Simple Additive Weighting method (SAW) and the Weighted Product method
1 Apichat Sopadang: MADM - Scoring Method 2

Apichat Sopadang: MADM Scoring Method

Simple Additive Weighting (SAW) Method


Best know and most widely used method Uses all n attribute values of an alternative and uses the regular arithmetical operations of multiplication and addition The attribute values must be both numerical and comparable
Vi = w j rij ,
j =1 n

SAW, Cont.

i = 1,..., m
Apichat Sopadang: MADM - Scoring Method 3 Apichat Sopadang: MADM - Scoring Method 4

Apichat Sopadang: MADM - Scoring Method

Apichat Sopadang: MADM - Scoring Method

Weight Product Method


Transformation is not necessary when we use multiplication among attribute values The weights become exponents associated with each attribute value Positive power for benefit attributes and negative n power for cost attributes w xij j V ( Ai ) j =1 Ri = V ( A* ) = n * w , i = 1,..., m (x j ) j
Apichat Sopadang: MADM - Scoring Method 7 Apichat Sopadang: MADM - Scoring Method

j =1

Weight Product Method, Cont.

TOPSIS
Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) Ideal solution is usually unattainable or infeasible DMs utilities decrease monotonically when an alternative moves away from this ideal TOPSIS defines an index called similarity to the positive-ideal solution (proximity to positive and remoteness to negative values)

Apichat Sopadang: MADM - Scoring Method

Apichat Sopadang: MADM - Scoring Method

10

TOPSIS, Cont.
1. Calculate normalized ratings 2. Calculate weight normalized ratings 3. Identify positive-ideal and negative-ideal solutions 4. Calculate separation measures
Si* =

TOPSIS, Cont.
5. Calculate similarities to positive-ideal solution
Ci* = Si , i = 1,..., m ( S i* + Si )

6. Rank preference order

(vij v*j ) 2 ,
j =1

Si =

(v
j =1

ij

v )2 , j

i = 1,..., m
11 Apichat Sopadang: MADM - Scoring Method 12

Apichat Sopadang: MADM - Scoring Method

TOPSIS, Cont.

Apichat Sopadang: MADM - Scoring Method

13

Apichat Sopadang: MADM - Scoring Method

14

Apichat Sopadang: MADM - Scoring Method

15

Apichat Sopadang: MADM - Scoring Method

16

ELECTRE METHOD
Management Science Multiple Attribute Decision Making By Dr. Apichat Sopadang

ELECTRE
Elimination et Choice Translating Reality Outrank relationship
A1($13000, 18MPG), A2($16000, 21MPG) and A3($18000, 25MPG) => nondominate (A1 R A2) and (A2 R A3) but not imply that (A1 R A3)

Pairwise comparison It examines both the degree to which the preference weights are in agreement with pairwise dominance relationships and the degree to which weighted evaluations differ from each other
17 Apichat Sopadang: MADM - Scoring Method 18

Apichat Sopadang: MADM Scoring Method

Outrank Relationship

Procedure of ELECTRE.
1. Calculate the normalized decision matrix 2. Calculate the weighted normalized decision matrix 3. Determine the concordance and discordance set
C(p,q) = {j|vpj vqj} D(p,q) = {j|vpj < vqj}

Apichat Sopadang: MADM - Scoring Method

19

Apichat Sopadang: MADM - Scoring Method

20

Procedure of ELECTRE.
4. Calculate the concordance matrix 5. Calculate the discordance matrix 6. Determine the concordance dominance matrix 7. Determine the discordance dominance matrix 8. Determine the aggregate dominance matrix 9. Eliminate the less favorable alternative
Apichat Sopadang: MADM - Scoring Method 21 Apichat Sopadang: MADM - Scoring Method 22

Apichat Sopadang: MADM - Scoring Method

23

Apichat Sopadang: MADM - Scoring Method

24

Apichat Sopadang: MADM - Scoring Method

25

Apichat Sopadang: MADM - Scoring Method

26

A2 and A4 can be eliminated

Apichat Sopadang: MADM - Scoring Method

27

Apichat Sopadang: MADM - Scoring Method

28

You might also like