Multiple-criteria decision analysis

From Wikipedia, the free encyclopedia

"MCDM" redirects here. For the use in cosmology, see meta-cold dark matter.
Plot of two criteria when maximizing return and minimizing risk in financial portfolios (Pareto-optimal points in red)
Multiple-criteria decision-making or multiple-criteria decision analysis (MCDA) is a sub-
discipline of operations researchthat explicitly considers multiple criteria in decision-making
environments. Whether in our daily lives or in professional settings, there are typically multiple
conflicting criteria that need to be evaluated in making decisions. Cost or price is usually one of the
main criteria. Some measure of quality is typically another criterion that is in conflict with the cost. In
purchasing a car, cost, comfort, safety, and fuel economy may be some of the main criteria we
consider. It is unusual to have the cheapest car to be the most comfortable and the safest.
In portfolio management, we are interested in getting high returns but at the same time reducing our
risks. Again, the stocks that have the potential of bringing high returns typically also carry high risks
of losing money. In a service industry, customer satisfaction and the cost of providing service are
two conflicting criteria that would be useful to consider.
In our daily lives, we usually weigh multiple criteria implicitly and we may be comfortable with the
consequences of such decisions that are made based on only intuition. On the other hand, when
stakes are high, it is important to properly structure the problem and explicitly evaluate multiple
criteria. In making the decision of whether to build a nuclear power plant or not, and where to build it,
there are not only very complex issues involving multiple criteria, but there are also multiple parties
who are deeply affected from the consequences.
Structuring complex problems well and considering multiple criteria explicitly leads to more informed
and better decisions. There have been important advances in this field since the start of the modern
multiple-criteria decision-making discipline in the early 1960s. A variety of approaches and methods,
many implemented by specialized decision-making software,
[1][2]
have been developed.
Solving MCDM problems[edit]
Different schools of thought have developed for solving MCDM problems (both of the design and
evaluation type). For a bibliometric study showing their development over time, see Bragge,
Korhonen, H. Wallenius and J. Wallenius [2010].
[14]

Multiple objective mathematical programming school
(1) Vector maximization: The purpose of vector maximization is to approximate the nondominated
set; originally developed for Multiple Objective Linear Programming problems (Evans and Steuer,
1973;
[15]
Yu and Zeleny, 1975
[16]
).
(2) Interactive programming: Phases of computation alternate with phases of decision-making
(Benayoun et al., 1971;
[17]
Geoffrion, Dyer and Feinberg, 1972;
[18]
Zionts and Wallenius,
1976;
[19]
Korhonen and Wallenius, 1988
[20]
). No explicit knowledge of the DMs value function is
assumed.
Goal programming school
The purpose is to set apriori target values for goals, and to minimize weighted deviations from these
goals. Both importance weights as well as lexicographic pre-emptive weights have been used
(Charnes and Cooper, 1961
[21]
).
Fuzzy-set theorists
Fuzzy sets were introduced by Zadeh (1965)
[22]
as an extension of the classical notion of sets. This
idea is used in many MCDM algorithms to model and solve fuzzy problems.
Multiattribute utility theorists
Multiattribute utility or value functions are elicited and used to identify the most preferred alternative
or to rank order the alternatives. Elaborate interview techniques, which exist for eliciting linear
additive utility functions and multiplicative nonlinear utility functions, are used (Keeney and Raiffa,
1976
[23]
).
French school
The French school focuses on decision aiding, in particular the ELECTRE family of outranking
methods that originated in France during the mid-1960s. The method was first proposed by Bernard
Roy (Roy, 1968
[24]
).
Evolutionary multiobjective optimization school (EMO)
EMO algorithms start with an initial population, and update it by using processes designed to mimic
natural survival-of-the-fittest principles and genetic variation operators to improve the average
population from one generation to the next. The goal is to converge to a population of solutions
which represent the nondominated set (Schaffer, 1984;
[25]
Srinivas and Deb, 1994
[26]
). More recently,
there are efforts to incorporate preference information into the solution process of EMO algorithms
(see Deb and Kksalan, 2010
[27]
).
Analytic hierarchy process (AHP)
The AHP first decomposes the decision problem into a hierarchy of subproblems. Then the decision-
maker evaluates the relative importance of its various elements by pairwise comparisons. The AHP
converts these evaluations to numerical values (weights or priorities), which are used to calculate a
score for each alternative (Saaty, 1980
[28]
). A consistency index measures the extent to which the
decision-maker has been consistent in her responses.
MCDM methods[edit]
The following MCDM methods are available, many of which are implemented by
specialized decision-making software:
[1][2]

Aggregated Indices Randomization Method (AIRM)
Analytic hierarchy process (AHP)
Analytic network process (ANP)
Data envelopment analysis
Decision EXpert (DEX)
Dominance-based rough set approach (DRSA)
ELECTRE (Outranking)
The evidential reasoning approach (ER)
Goal programming
Grey relational analysis (GRA)
Inner product of vectors (IPV)
Measuring Attractiveness by a categorical Based Evaluation Technique (MACBETH)
Disaggregation Aggregation Approaches (UTA*, UTAII, UTADIS)
Multi-Attribute Global Inference of Quality (MAGIQ)
Multi-attribute utility theory (MAUT)
Multi-attribute value theory (MAVT)
New Approach to Appraisal (NATA)
Nonstructural Fuzzy Decision Support System (NSFDSS)
Potentially all pairwise rankings of all possible alternatives (PAPRIKA)
PROMETHEE (Outranking)
Superiority and inferiority ranking method (SIR method)
Technique for the Order of Prioritisation by Similarity to Ideal Solution (TOPSIS)
Value analysis (VA)
Value engineering (VE)
VIKOR method
[29]

Fuzzy VIKOR method
[30]

Weighted product model (WPM)
Weighted sum model (WSM)

Value engineering
From Wikipedia, the free encyclopedia
Value engineering (VE) is a systematic method to improve the "value" of goods or products and
services by using an examination of function. Value, as defined, is the ratio of function to cost. Value
can therefore be increased by either improving the function or reducing the cost. It is a primary tenet
of value engineering that basic functions be preserved and not be reduced as a consequence of
pursuing value improvements.
[1]

The reasoning behind value engineering is as follows: if marketers expect a product to become
practically or stylistically obsolete within a specific length of time, they can design it to only last for
that specific lifetime. The products could be built with higher-grade components, but with value-
engineering they are not because this would impose an unnecessary cost on the manufacturer, and
to a limited extend also an increased cost on the purchaser. Value engineering will reduce these
costs. A company will typically use the least expensive components that satisfy the product's lifetime
projections.
Due to the very short life spans however which is often a result of this "value engineering technique"
planned obsolescence has become associated with product deterioration and inferior quality. Vance
Packard once claimed this practice gave engineering as a whole a bad name, as it directed creative
engineering energies toward short-term market ends. Philosophers such as Herbert
Marcuse and Jacque Fresco have also criticized the economic and societal implications of this
model.
The Job Plan[edit]
Value engineering is often done by systematically following a multi-stage job plan. Larry Miles'
original system was a six-step procedure which he called the "value analysis job plan." Others have
varied the job plan to fit their constraints. Depending on the application, there may be four, five, six,
or more stages. One modern version has the following eight steps:
1. Preparation
2. Information
3. Analysis
4. Creation
5. Evaluation
6. Development
7. Presentation
8. Follow-up
Four basic steps in the job plan are:
Information gathering - This asks what the requirements are for the object. Function analysis, an
important technique in value engineering, is usually done in this initial stage. It tries to determine
what functions or performance characteristics are important. It asks questions like; What does
the object do? What must it do? What should it do? What could it do? What must it not do?
Alternative generation (creation) - In this stage value engineers ask; What are the various
alternative ways of meeting requirements? What else will perform the desired function?
Evaluation - In this stage all the alternatives are assessed by evaluating how well they meet the
required functions and how great the cost savings will be.
Presentation - In the final stage, the best alternative will be chosen and presented to the client
for final decision.
How it works[edit]
VE follows a structured thought process to evaluate options as follows.
Gather information
1.What is being done now?
Who is doing it?
What could it do?
What must it not do?
Measure
2.How will the alternatives be measured?
What are the alternate ways of meeting
requirements?
What else can perform the desired function?
Analyze
3.What must be done?
What does it cost?
Generate
4.What else will do the job?
Evaluate
5.Which Ideas are the best?
Develop and expand ideas
6.What are the impacts? 7.What is the cost?
8.What is the performance?
Present ideas
9.Sell alternatives