Manifold Learning for Innovation Funding: Identification of Potential Funding Recipients

Vincent Grollemund (1) , Gaétan Le Chat , Jean-François Pradat-Peyre (2, 1) , François Delbot (3)

1 MoVe - Modélisation et Vérification
2 UPN - Université Paris Nanterre
3 RO - Recherche Opérationnelle

finElink is a recommendation system that provides guidance to French innovative companies with regard to their financing strategy through public funding mechanisms. Analysis of financial data from former funding recipients partially feeds the recommendation system. Financial company data from a representative French population are reduced and projected onto a two-dimensional space with Uniform Manifold Approximation and Projection, a manifold learning algorithm. Former French funding recipients’ data are projected onto the two-dimensional space. Their distribution is non-uniform, with data concentrating in one region of the projection space. This region is identified using Density-based Spatial Clustering of Applications with Noise. Applicant companies which are projected within this region are labeled potential funding recipients and will be suggested the most competitive funding mechanisms

Mots clés: Dimension reduction; Manifold learning; Clustering

Domaines: Environnements Informatiques pour l'Apprentissage Humain

Vincent Grollemund, Gaétan Le Chat, Jean-François Pradat-Peyre, François Delbot. Manifold Learning for Innovation Funding: Identification of Potential Funding Recipients. 16th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Jun 2020, Neos Marmaras, Greece. pp.119 - 127, ⟨10.1007/978-3-030-49161-1_11⟩. ⟨hal-03401744⟩