DynaNorm
Project Summary
Data normalization is essential for all kinds of decision-making
problems because data has to be numerical and comparable to be aggregated
into alternatives´ scores and then chose the best alternative
(highest score). In multi-criteria decision-making (MCDM), normalization
is the first step that converts criteria values into a common scale,
thus enabling rating and ranking of alternatives.
Many multi-criteria decision-making methods use normalization techniques,
which neither take into account the type of data nor if its normalization
truly represents a mapping from source data to a representative
scale. Although there are some attempts in the literature, to address
the subject of normalization, there is still an important open question"
which technique is more appropriate for usage on well-known MCDM
methods?".
Hence, the main objective of this study is to develop an assessment
evaluation framework for analyzing and recommending which are the
best normalization techniques for multi-criteria decision methods.
Also, we will prepare a taxonomy for normalization techniques and
describe their advantages and disadvantages.
To validate and test the framework we will devise a validation strategy
for comparing the normalization techniques and then explore the
role of normalization techniques for two emergent topics in decision
making, dynamic multi criteria decision making (DMCDM) and collaborative
decision making, specifically related with problems of selection
of suppliers, business partners, resources etc.
|
|