Espinosa Blasco, Mónica, Penagos-Londoño, Gabriel Ignacio, Ruiz Moreno, Felipe, Vilaplana-Aparicio, Maria J. New Insights on the Allocation of Innovation Subsidies: A Machine Learning Approach Journal of the Knowledge Economy. 2023. https://doi.org/10.1007/s13132-023-01295-9 URI: http://hdl.handle.net/10045/132948 DOI: 10.1007/s13132-023-01295-9 ISSN: 1868-7865 (Print) Abstract: Gaining more insights on how R&D&i subsidies are allocated is highly relevant for companies and policymakers. This article provides new evidence of the identification of some key drivers for companies participating in R&D&i project selection processes. It extends the existing literature by providing insight based on sophisticated, accurate methodology. A metaheuristic optimization algorithm is employed to select the most useful variables. Their importance is then ranked using a machine learning process, namely a random forest. A sample of 1252 cases of R&D&i subsidies is used for more than 800 companies based in Spain between 2014 and 2018. The study contributes by providing useful knowledge into how the value of received subsidies are associated with some firm characteristics. The findings allow the implementation of transparent public innovation policies and the reduction of the gap between the aspects that are considered important and those that actually determine the destination of these subsidies. Keywords:Innovation, Subsidies, R&D&i strategy, Valencian companies, Random forest Springer Nature info:eu-repo/semantics/article