Innovative propensity with a fuzzy multicriteria approach Analysis of the Spanish industrial sector with data mining techniques

Purpose Although R&D plays a crucial role in innovativeness and R&D expenditures is the most widely used tool to measure the level of innovativeness of companies, other variables and inputs may be equally interesting. The purpose of this paper is to define an innovative propensity index (IPI) which considers these variables and allows the identification of those companies which have a higher propensity to implement different types of innovativeness. Design/methodology/approach Taking into account, the different criteria that may be considered in an IPI and that the perception of the relative importance of each criterion is subjective, the use of an innovativeness multicriteria decision methodology has been considered appropriate. In particular, an IPI is built from the weighting of the criteria through FAHP methodology. Data mining techniques are subsequently used to establish a non-supervised ranking (clustering) of a sample of firms, considering their IPI values. Findings The application of an IPI to a sample of 1,639 companies operating in different industrial sectors has helped us to find out that this index is useful for identifying those companies which really show an increased innovative capacity. A comparative analysis by sectors has shown that although there are companies from all sectors with a high innovative propensity, the proportion increases in more technological sectors. Moreover, it has been observed that in companies with higher net personnel expenses and high productivity level the innovative propensity is also higher. Originality/value The criteria used to build the index affects innovativeness individually, but the value of the analysis lies in its multicriteria approach and use of fuzzy logic. The validation of the index in a wide sample of firms is another outstanding aspect of the analysis.