Modelling innovation performance of European regions using multi-output neural networks

Abstract

Regional innovation performance is an important indicator for decision-making regarding the implementation of policies intended to support innovation. However, patterns in regional innovation structures are becoming increasingly diverse, complex and nonlinear. To address these issues, this study aims to develop a model based on a multi-output neural network. Both intra- and inter-regional determinants of innovation performance are empirically investigated using data from the 4th and 5th Community Innovation Surveys of NUTS 2 (Nomenclature of Territorial Units for Statistics) regions. The results suggest that specific innovation strategies must be developed based on the current state of input attributes in the region. Thus, it is possible to develop appropriate strategies and targeted interventions to improve regional innovation performance. We demonstrate that support of entrepreneurship is an effective instrument of innovation policy. We also provide empirical support that both business and government R&D activity have a sigmoidal effect, implying that the most effective R&D support should be directed to regions with below-average and average R&D activity. We further show that the multi-output neural network outperforms traditional statistical and machine learning regression models. In general, therefore, it seems that the proposed model can effectively reflect both the multiple-output nature of innovation performance and the interdependency of the output attributes.

Different Influence of Cooperation and Public Funding on Innovation Activities Within German Industries

“…-Innovation while different innovation activities significantly influence the firm performance (Camisón & Villar-López, 2014). However, patterns in innovation structures are becoming increasingly diverse, complex and nonlinear (Hajek & Henriques, 2017) and, therefore, there are growing significant differences in innovation activities and performance. Therefore, there is a need to distinguish between different types of innovation (e.g.…”

The role of foreign technologies and R&D in innovation processes within catching-up CEE countries

“…the most accurate results in comparison with other techniques including for example logistic regression, radial basis function, self-organizing feature maps [82] and whose learning capability makes them very suitable for different specific applications including pattern recognition or data classification [83]. On the other hand, RF represent a combination of tree predictors…”

Machine Learning Approach for National Innovation Performance Data Analysis

“…Recent studies therefore use machine learning techniques to overcome these limitations. Hajek and Henriques (2017) demonstrated in their study, that the importance of determinants of regional innovation performance can be identified using multi-output neural networks. However, the determinants used for analysis have been evaluated empirically based on two community innovation surveys instead of applying unsupervised feature selection.…”