| Summary: | When multi-criteria decision making, decision makers will expend
significant effort in selecting a data normalization method and a weighting
method. If a mistake is made in those choices, it will result in decisions that
do not find the best solution. Furthermore, with qualitative criteria, it is
impossible to standardize the data. Similarly, determining the weights of
criteria will be difficult if the criteria are in qualitative form. R and CURLI are
two multi-criteria decision-making methods that do not require data
normalization or the use of additional weighting methods for the criteria.
They are therefore well suited for ranking alternatives when the criteria are
both quantitative and qualitative. This study compares the two methods
through three examples from different fields. The results show that these
two methods jointly determine the best solution in all three fields and are
also suitable when using other decision-making methods that require data
normalization and have high requirements using the method of
determining the weights for the criteria.
|
|---|