A peer IF-TOPSIS based decision support system for packaging machine selection Davide Aloini ⇑ , Riccardo Dulmin, Valeria Mininno University of Pisa, L.go L. Lazzarino, Pisa, Italy article info Keywords: Intuitionistic fuzzy set TOPSIS method Peer group decision making Machine selection abstract Selecting the appropriate manufacturing machine is a very important and complex problem for firms which usually have to deal with both qualitative and quantitative criteria and involve different decision makers whose knowledge is often vague and imprecise. This paper proposes a peer-based modification to intuitionistic fuzzy multi-criteria group decision making with TOPSIS method (peer IF-TOPSIS) and applies it to a packaging machine selection problem. Intuitionistic fuzzy weighted averaging (IFWA) operator has been selected both to obtain the group opin- ion on the relevance of the single decision makers and to aggregate individual opinions of decision mak- ers for rating the importance of criteria and alternatives. A case study illustrates the application of the modified IF-TOPSIS method in order to select a Vertical Form Fill and Seal (VFFS) for Double Square Bottom Bag (DSBB) machine in food packaging. Ó 2013 Elsevier Ltd. All rights reserved. 1. Introduction Manufacturing companies worldwide are forced to undergo transformation processes in order to improve their ability to suc- ceed with their products on extremely competitive international markets. In this perspective, an adequate selection of the appropri- ate machine tools if often crucial but very difficult to achieve. Advanced manufacturing technology, in fact, requires a high le- vel of initial investment and usually deals with both qualitative and quantitative benefits which make the traditional investment model based on Return On Investment (ROI), Cash Flow Analysis (CF), Pay-Back (PB) and Net Present Value (NPV) not really suitable. Arguably these models emphasize quantitative and financial anal- ysis, but fail to capture many of the ‘‘intangible’’ benefits such as greater manufacturing flexibility, improved product quality, quick response to customer demand and better employee safety and motivation (Abdel-Kader, 1997; Chen & Small, 1996; Kaplan, 1986) which are typically more challenging to measure and mon- etize, or they are not at all. The high investment risk inherent in advanced manufacturing technology often leads to the use of arbitrarily high hurdle dis- counts rates (Accola, 1994; Kaplan, 1986; Kaplan & Atkinsons, 1989). Moreover, adjustments to the discount rate are affected by decision maker’s attitude toward the specific risk rather than by an explicit representation of the risks inherent in the invest- ment alternatives (Accola, 1994). Finally, also when risk is explic- itly assessed and systematically included into the investment evaluation, as for example by using innovative evaluation para- digms such as Real Option Approach (ROA), the problem of esti- mating returns from intangibles still remain unsolved. This condition often results in a severe and sometime irreparable eval- uation bias affecting the final decision. In order to solve this gap and according to Lefley (1996), we think a more sophisticated (and not financial) approach is needed to the appraisal of a machine selection, which could take into ac- count the strategic nature and the full benefits from such invest- ments. The most adopted procedures in literature are Multi Criteria Decision Analysis (MCDA) or Multi Criteria Decision Mak- ing (MDCM) methods, often combined with fuzzy logic or subse- quent evolution of fuzzy set theory in order to deal with the vagueness and imprecision inherent with advanced manufacturing technology selection problem. This paper proposes a modified version of Boran, Genç, Kurt, and Akay (2009) fuzzy multi-criteria decision making with TOPSIS method which is inspired by a peer-based view of judgments. Dif- ferently from the previous version of the algorithm we advance a peer procedure for determining the weights of Decision Makers’ opinions. Thus, Intuitionistic Fuzzy Weighted Averaging (IFWA) operator is used to obtain the group opinion on the relevance of the single decision makers. In a high uncertain environment, in fact, a single supervisor can be subjected to a significant bias when assessing weights to the subjects involved in the decision process, 0957-4174/$ - see front matter Ó 2013 Elsevier Ltd. All rights reserved. http://dx.doi.org/10.1016/j.eswa.2013.09.014 ⇑ Corresponding author. Address: Department of Energy, System, Land and Construction Engineering, University of Pisa, L.go L. Lazzarino, 56122 Pisa, Italy. Tel.: +39 50 2217088; fax: +39 50 2217333. E-mail addresses: Davide.Aloini@dsea.unipi.it (D. Aloini), Riccardo.Dulmin@d- sea.unipi.it (R. Dulmin), Valeria.Mininno@dsea.unipi.it (V. Mininno). Expert Systems with Applications 41 (2014) 2157–2165 Contents lists available at ScienceDirect Expert Systems with Applications journal homepage: www.elsevier.com/locate/eswa