Methodology by: Luis Dias and João Clímaco
Software design and development by: Luis Dias
The VIP (Variable Interdependent Parameters) Analysis software has been built to support the selection of the most preferred alternative among a list, considering the impacts of each alternative on multiple evaluation criteria. It is based on an additive aggregation model (value function), accepting imprecise information on the value of the scaling coefficients (a.k.a. scaling constants, which indirectly reflect the relative importance of the each criterion).
Rather than precise values, the scaling coefficients are considered Variable Interdependent Parameters subject to a set of constraints (e.g. bounds, order relations, or any linear constraints). This amounts to consider multiple acceptable combinations of values for these parameters, which is particularly relevant in spite of the simplicity of the model. Indeed, fixing precise values for the scaling constants is often difficult because these values reflect the judgments of the decision makers, which may evolve through time and may be hard to elicit in a precise way. The number of (arbitrary) options in the process of building the criteria plus the possibility of divergence among several decision makers may further hinder the requirement of precise numerical figures.
The VIP Analysis software offers its users an easy to use tool to analyze a choice problem using multiple approaches at several levels of detail, when imprecise information is accepted. It computes the best and worst overall value that each alternative may attain (given the multiple acceptable inputs), the pairwise confrontation table (differences of global value between pairs of alternatives) - which allows to discover dominated or quasi-dominated alternatives -, as well as the maximum loss of opportunity associated with choosing each alternative, plus the domain where each alternative is optimal or quasi-optimal (if the problem dimension allows it).
This research project has been partially financed by the FCT (Portuguese Foundation for Science and Technology) grants PRAXIS/PCSH/P/CEG/28/96 (co-financed by EC's Second Framework Programme 1994/99) and POSI/SRI/37346/2001 (co-financed by EC's Third Framework Programme 2000/2006).
VIP Analysis has been requested by over two hundred users from several countries, besides Portugal: Argentina, Australia, Austria, Bangladesh, Belgium, Brazil, Canada, Chile, China & Taiwan, Colombia, Costa Rica, Cuba, Czech Rep., Ecuador, Egypt, Finland, France, Germany, Greece, Hungary, Indonesia, Iran, Italy, Japan, Lithuania, Malaysia, Maroc, Mexico, The Netherlands, New Zealand, Poland, Romania, Russia, Slovenia, Spain, Switzerland, UK, USA, Venezuela and Vietnam.
VIP Analysis is distributed for free. Interested persons may send me an e-mail requesting the software, indicating their name, their institutional affiliation and type of activity, address, and the reason for the interest in the software. Request VIP Analysis
Dias, L. C. and J. N. Clímaco, "Additive Aggregation with Variable Interdependent Parameters: the VIP Analysis Software", Journal of the Operational Research Society, Vol. 51, No. 9, pp. 1070-1082, 2000.
VIP Analysis has also been integrated in Decision Desktop as a plug-in. When compared with the original standalone VIP Analysis, the main innovation of the VIP Analysis plug-in is to allow several users working on the same problem under different roles: coordinator, evaluator, and decision-maker, thus defining a workflow process and enabling concurrent and remote access to the data over a network. By being included in the Decision Deck platform, VIP Analysis is now integrated with other decision aiding methods within a coherent interface. A final advantage is that the platform is open-source, which facilitates customization and collaborative improvement of the software. On the other hand, Decision Desktop requires access to a MySQL database and no longer allows file editing and saving for inputs and outputs.
Acknowledgements: Quorum project, VRTUOSI project (multicriteria decision analysis online course)
Reference: Clímaco, J.N., J.A. Costa, L. C. Dias, P. Melo, “Supporting collaborative multi-criteria evaluation: the VIP Analysis plug-in for Decision Deck”, International Journal of Decision Support System Technology, Vol. 1, No. 4, 1-15, 2009.