Semantic search in SME networks to evaluate their collaborative assets

The need to compete in a globalized market, but also the aspiration to provide sufficient stability for their own small business, drives Small and Medium Enterprises (SMEs) to aggregate in industrial networks, sharing objectives and strategies with other SMEs, while preserving their own individual autonomy. The goal of this paper is to offer an unbiased method to analyze the collaboration opportunities of existing SME networks, without relying only on subjective data. The difficulty in the classification of the collaborative models is that it must be extracted from objective parameters based of public data available on the web. To this aim, a semantic model is used to automatically extract information from unstructured texts. Then, we reconstruct the graph of existing collaborations among the companies, which depends on the activity they performed. Eventually the network graph is used to estimate the potential collaboration of a new company joining the network.