A web tool to support decision making in the housing market using hesitant fuzzy linguistic term sets

In this paper we present a linguistic multiple-expert multi-criteria decision making model and a web tool to support it, that is centred on the housing market. The web tool is integrated with the usual catalogue of resources for rental or for sale, enriched with the possibility of ranking a subset of properties according to the client’s preferences and the internal knowledge associated to the properties. Usually the description of a property is quantitative, thought in our case we add qualitative information corresponding to assessments made by housing agents. These agents are considered experts in the market conditions. esitant fuzzy linguistic term set inguistic 2-tuples ulticriteria decision making eb services We apply the 2-tuple linguistic representation model to keep accuracy in the processes of Computing with Words and the hesitant fuzzy linguistic term sets to qualify in situations of uncertainty and hesitation in the assessments. The software helps the agents in the process of the elicitation of the linguistic expression based on the fuzzy linguistic approach and the use of context-free grammars, and the web visitin ousing market clients in the decision of . IntroductionIntroduction Every day people are challenged with multiple acts of deciion. It is a natural human activity that is prompt to be subjective n its basis, but also to be uncertain and imprecise. Sometimes e are not aware of the implicit complexity of a problem, xcept when we try to make decisions with computational modls. Problems defined under uncertain conditions are common n real world, but quite challenging to be modelled in a comuter program due to the difficulty of dealing with uncertain nformation. Computing with Words (CW) [30] is a methodolgy for reasoning and computing with perceptions rather than easurements. CW is able to empower applications that involve eople expressing their preferences which happens in linguisic Decision Making (DM): the experts assess the potential of n alternative through qualitative values rather than quantitative nes. Some models have been proposed to operate with linguistic nformation [1,6,16]. In this work we operate with the fuzzy linuistic approach, that represents qualitative aspects as linguistics alues by means of linguistics variables [29]. These models are referable because experts are allowed to evaluate closer to natural ∗ Corresponding author. Tel.: +34 615329988. E-mail addresses: [email protected] (R. Montes), [email protected] (A.M. Sánchez), [email protected] (P. Villar), [email protected] (F. Herrera). ttp://dx.doi.org/10.1016/j.asoc.2015.01.030 568-4946/© 2015 Elsevier B.V. All rights reserved. g a property. © 2015 Elsevier B.V. All rights reserved. language and the way people reason. Criteria in different problems may vary, for example, if we describe a car, the criteria would involve price, fuel consumption or comfort. On the other hand, it is sometimes difficult to give an opinion as an exact single label, though we could allow to work with some possible set of values for decision makers. To manage linguistic information in DM a well known computational model that carries out CW processes without loss of information is the 2-tuple Linguistic Computational Model [8]. This model uses a pair of values called linguistic 2-tuple to represent the linguistic information. Many extensions to the 2-tuple linguistic model have been developed: to deal with unbalanced linguistic information [11] where the linguistic labels in the terms set are not evenly distributed around a central term, or to deal with multi-granular label sets [10]. A generalization of the 2-tuple representation, the proportional 2-tuple models were developed by Wang and Hao in [24]. Also, Dong et al. [3,4] explored the concept of numerical scale, which extends the linguistic 2-tuple and the proportional 2-tuple. Recently it has been enabled in DM problems the possibility of provide inaccurate rates and comparative linguistic expressions by means of the use of a context-free grammar represented by a hesitant fuzzy linguistic term set (HFLTS) [13,18]. This way to deal with uncertainty and hesitation in the context of fuzzy decision making, derives from the original idea of Torra’s hesitant fuzzy sets [22], has been applied in many recent works [2,12–15,17,19,20,26,25,23,31,32].