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.

Institute of System Engineering and Informatics Faculty of Economics and Administration University of Pardubice Studentská 84 Pardubice Czech Republic

ISEGI Universidade Nova de Lisboa Lisboa Portugal

Erratum In

PLoS One. 2017 Dec 8;12(12):e0189746. doi: 10.1371/journal.pone.0189746. PubMed

See more in PubMed

Mention AL. Co-operation and co-opetition as open innovation practices in the service sector: Which influence on innovation novelty? Technovation. 2011;31: 44–53. doi: 10.1016/j.technovation.2010.08.002 DOI

Cooke P. Knowledge economies. Clusters, learning and cooperative advantage [Internet]. Routledge studies in international business and the world economy. London: Routledge; 2002. doi: 10.4324/9780203445402 DOI

Hajek P, Henriques R, Hajkova V. Visualising components of regional innovation systems using self-organizing maps—Evidence from European regions. Technol Forecast Soc Change. 2014;84: 197–214. doi: 10.1016/j.techfore.2013.07.013 DOI

Lau AKW, Lo W. Regional innovation system, absorptive capacity and innovation performance: An empirical study. Technol Forecast Soc Change. 2015;92: 99–114. doi: 10.1016/j.techfore.2014.11.005 DOI

Doloreux D. Regional innovation systems in the periphery: The case of the Beauce in Québec (Canada). Int J Innov Manag. 2003;7: 67–94. doi: 10.1142/S1363919603000738 DOI

Tödtling F, Trippl M. One size fits all? Res Policy. 2005;34: 1203–1219. doi: 10.1016/j.respol.2005.01.018 DOI

Vega-Jurado J, Gutiérrez-Gracia A, Fernández-de-Lucio I, Manjarrés-Henríquez L. The effect of external and internal factors on firms’ product innovation. Res Policy. 2008;37: 616–632. doi: 10.1016/j.respol.2008.01.001 DOI

Caloghirou Y, Kastelli I, Tsakanikas A. Internal capabilities and external knowledge sources: Complements or substitutes for innovative performance? Technovation. 2004;24: 29–39. doi: 10.1016/S0166-4972(02)00051-2 DOI

Mitze T, Alecke B, Reinkowski J, Untiedt G. Linking collaborative R&D strategies with the research and innovation performance of SMEs in peripheral regions: Do spatial and organizational choices make a difference? Ann Reg Sci. 2015;55: 555–596. doi: 10.1007/s00168-015-0719-4 DOI

Grillitsch M, Nilsson M. Innovation in peripheral regions: Do collaborations compensate for a lack of local knowledge spillovers? Ann Reg Sci. 2015;54: 299–321. doi: 10.1007/s00168-014-0655-8 DOI

Roper S, Love JH, Bonner K. Firms’ knowledge search and local knowledge externalities in innovation performance. Res Policy. 2017;46: 43–56. doi: 10.1016/j.respol.2016.10.004 DOI

D’Ambrosio A, Gabriele R, Schiavone F, Villasalero M. The role of openness in explaining innovation performance in a regional context. J Technol Transf. 2017;42: 389–408. doi: 10.1007/s10961-016-9501-8 DOI

Hollanders H. Measuring Regional Innovation: A European Perspective. Glob Innov Index 2013 Local Dyn Innov. 2013; 79–85.

Brem A, Voigt KI. Integration of market pull and technology push in the corporate front end and innovation management-Insights from the German software industry. Technovation. 2009;29: 351–367. doi: 10.1016/j.technovation.2008.06.003 DOI

Wang TY, Chien SC. Forecasting innovation performance via neural networks—A case of Taiwanese manufacturing industry. Technovation. 2006;26: 635–643. doi: 10.1016/j.technovation.2004.11.001 DOI

Chien SC, Wang TY, Lin SL. Application of neuro-fuzzy networks to forecast innovation performance—The example of Taiwanese manufacturing industry. Expert Syst Appl. 2010;37: 1086–1095. doi: 10.1016/j.eswa.2009.06.107 DOI

Saberi S, Yusuff RM. Neural network application in predicting advanced manufacturing technology implementation performance. Neural Comput Appl. 2012;21: 1191–1204. doi: 10.1007/s00521-010-0507-0 DOI

de la Paz-Marín M, Campoy-Muñoz P, Hervás-Martínez C. Non-linear multiclassifier model based on Artificial Intelligence to predict research and development performance in European countries. Technol Forecast Soc Change. 2012;79: 1731–1745. doi: 10.1016/j.techfore.2012.06.001 DOI

Detienne KB, Detienne DH, Joshi S a. Neural networks as statistical tools for business researchers. Organ Res Methods. 2003;6: 236–265. doi: 10.1177/1094428103251907 DOI

Katz J. What is a complex innovation system? PLoS One. 2016;11: e0156150 doi: 10.1371/journal.pone.0156150 PubMed DOI PMC

Buesa M, Heijs J, Baumert T. The determinants of regional innovation in Europe: A combined factorial and regression knowledge production function approach. Res Policy. 2010;39: 722–735. doi: 10.1016/j.respol.2010.02.016 DOI

Fritsch M, Meschede M. Product innovation, process innovation, and size. Rev Ind Organ. 2001;19: 335–350. doi: 10.1023/A:1011856020135 DOI

Radosevic S. Regional innovation systems in Central and Eastern Europe: Determinants, organizers and alignments. J Technol Transf. 2002;27: 87–96.

Samara E, Georgiadis P, Bakouros I. The impact of innovation policies on the performance of national innovation systems: A system dynamics analysis. Technovation. 2012;32: 624–638. doi: 10.1016/j.technovation.2012.06.002 DOI

Bathelt H, Malmberg A, Maskell P. Clusters and knowledge: local buzz, global pipelines and the process of knowledge creation. Prog Hum Geogr. 2004;28: 31–56. doi: 10.1191/0309132504ph469oa DOI

Rodriguez-Pose A, Crescenzi R. Research and development, spillovers, innovation systems, and the genesis of regional growth in Europe. Reg Stud. 2008;42: 51–67. doi: 10.1080/00343400701654186 DOI

Navarro M, Gibaja JJ, Bilbao-Osorio B, Aguado R. Patterns of innovation in EU-25 regions: a typology and policy recommendations. Environ Plan C Gov Policy. SAGE Publications; 2009;27: 815–840.

Fritsch M, Slavtchev V. How does industry specialization affect the efficiency of regional innovation systems? Ann Reg Sci. 2010;45: 87–108. doi: 10.1007/s00168-009-0292-9 DOI

De Bruijn P, Lagendijk A. Regional innovation systems in the Lisbon strategy. Eur Plan Stud. 2005;13: 1153–1172. doi: 10.1080/09654310500336519 DOI

Huggins R, Izushi H, Prokop D, Thompson P. Regional evolution and waves of growth: A knowledge-based perspective. Expert Syst Appl. 2014;41: 5573–5586. doi: 10.1016/j.eswa.2014.02.008 DOI

Hollanders H. 2006 European Regional Innovation Scoreboard (2006 RIS). Rep Novemb. 2006;15.

Sleuwaegen L, Boiardi P. Creativity and regional innovation: Evidence from EU regions. Res Policy. 2014;43: 1508–1522. doi: 10.1016/j.respol.2014.03.014 DOI

Crescenzi R, Rodriguez-Pose A. Infrastructure and regional growth in the european union. Pap Reg Sci. 2012;91: 487–513. doi: 10.1111/j.1435-5957.2012.00439.x DOI

Casi L, Resmini L. Spatial complexity and interactions in the FDI attractiveness of regions. Pap Reg Sci. 2014;93: S51–S78. doi: 10.1111/pirs.12100 DOI

Huang L, Liu X, Xu L. Regional innovation and spillover effects of foreign direct investment in China: A threshold approach. Reg Stud. 2012;46: 583–596. doi: 10.1080/00343404.2010.520694 DOI

Munari F, Toschi L. Assessing the impact of public venture capital programmes in the United Kingdom: Do regional characteristics matter? J Bus Ventur. 2015;30: 205–226. doi: 10.1016/j.jbusvent.2014.07.009 DOI

Frenz M, Ietto-Gillies G. The impact on innovation performance of different sources of knowledge: Evidence from the UK Community Innovation Survey. Res Policy. 2009;38: 1125–1135. doi: 10.1016/j.respol.2009.05.002 DOI

Sáenz-Royo C, Gracia-Lázaro C, Moreno Y. The role of the organization structure in the diffusion of innovations. PLoS One. 2015;10: e0126076 doi: 10.1371/journal.pone.0126076 PubMed DOI PMC

OECD. Frascati Manual: Proposed Standard Practice for Surveys on Research and Experimental Development [Internet]. The Measurement of Scientific and Technological Activities. 2002. doi: 10.1787/9789264199040-en DOI

Zabala-Iturriagagoitia JM, Voigt P, Gutiérrez-Gracia A, Jiménez-Sáez F. Regional innovation systems: How to assess performance. Reg Stud. 2007;41: 661–672. doi: 10.1080/00343400601120270 DOI

Laursen K, Salter A. Open for innovation: The role of openness in explaining innovation performance among U.K. manufacturing firms. Strateg Manag J. 2006;27: 131–150. doi: 10.1002/smj.507 DOI

Ketata I, Sofka W, Grimpe C. The role of internal capabilities and firms’ environment for sustainable innovation: evidence for Germany. R&D Manag. 2014; n/a-n/a. doi: 10.1111/radm.12052 DOI

Gómez J, Salazar I, Vargas P. Sources of information as determinants of product and process innovation. PLoS One. 2016;11: e0152743 doi: 10.1371/journal.pone.0152743 PubMed DOI PMC

Inoue H, Liu Y. Revealing the intricate effect of collaboration on innovation. PLoS One. 2015;10: e0121973 doi: 10.1371/journal.pone.0121973 PubMed DOI PMC

Di Cagno D, Fabrizi A, Meliciani V, Wanzenböck I. The impact of relational spillovers from joint research projects on knowledge creation across European regions. Technol Forecast Soc Change. 2016;108: 83–94. doi: 10.1016/j.techfore.2016.04.021 DOI

Morrison A, Rabellotti R, Zirulia L. When do global pipelines enhance the diffusion of knowledge in clusters? Econ Geogr. 2013;89: 77–96. doi: 10.1111/j.1944-8287.2012.01167.x DOI

Huggins R, Thompson P. Entrepreneurship, innovation and regional growth: a network theory. Small Bus Econ. 2015;45: 103–128. doi: 10.1007/s11187-015-9643-3 DOI

Lundvall B. National innovation systems—Analytical concept and development tool. Ind Innov. 2007;14: 95–119. doi: 10.1080/13662710601130863 DOI

Archibugi D, Denni M, Filippetti A. The technological capabilities of nations: The state of the art of synthetic indicators. Technol Forecast Soc Change. 2009;76: 917–931. doi: 10.1016/j.techfore.2009.01.002 DOI

Bottazzi L, Peri G. Innovation and spillovers in regions: Evidence from European patent data. Eur Econ Rev. 2003;47: 687–710. doi: 10.1016/S0014-2921(02)00307-0 DOI

Vila LE, Cabrer B, Pavía JM. On the relationship between knowledge creation and economic performance. Technol Econ Dev Econ. Taylor & Francis; 2015;21: 539–556.

Tavassoli S, Carbonara N. The role of knowledge variety and intensity for regional innovation. Small Bus Econ. 2014;43: 493–509. doi: 10.1007/s11187-014-9547-7 DOI

Cappelen A, Castellacci F, Fagerberg J, Verspagen B. The impact of regional support on growth and convergence in the European Union. J Commen Mark Stud. 2003;41: 621–644. doi: 10.1111/1468-5965.00438 DOI

Brenner T, Broekel T. Methodological issues in measuring innovation performance of spatial units. Ind Innov. 2011;18: 7–37. doi: 10.1080/13662716.2010.528927 DOI

Dijkstra L, Annoni P, Kozovska K. A new regional competitiveness index: Theory, methods and findings. European Union Regional Policy Working Papers, n. 02/2011. Luxemburg; 2011.

Pakath R, Zaveri JS. Specifying critical inputs in a genetic algorithm-driven decision support system: An automated facility. Decis Sci. 1995;26: 749–771. doi: 10.1111/j.1540-5915.1995.tb01574.x DOI

Tsai CF, Hsiao YC. Combining multiple feature selection methods for stock prediction: Union, intersection, and multi-intersection approaches. Decis Support Syst. 2010;50: 258–269. doi: 10.1016/j.dss.2010.08.028 DOI

Hajek P, Michalak K. Feature selection in corporate credit rating prediction. Knowledge-Based Syst. 2013;51: 72–84. doi: 10.1016/j.knosys.2013.07.008 DOI

Gurney K. An Introduction to Neural Networks. Bristol, PA, USA: Taylor & Francis, Inc.; 1997.

Rumelhart DE, McClelland JL, Williams RJ. Parallel Distributed Processing: Explorations in the Microstructure of Cognition [Internet]. Computational Models of Cognition and Perception. 1986. doi: 10.1017/CBO9781107415324.004 DOI

Qi M, Zhang GP. Trend time-series modeling and forecasting with neural networks. IEEE Trans Neural Networks. 2008;19: 808–816. doi: 10.1109/TNN.2007.912308 PubMed DOI

Rao Y, Hadri K, Bu R. Testing for stationarity in heterogeneous panel data in the case of model misspecification. Bull Econ Res. 2010;62: 209–225. doi: 10.1111/j.1467-8586.2009.00327.x DOI

More JJ. The Levenberg-Marquardt algorithm: Implementation and theory. Lect Notes Math. 1978;630: 105–116. doi: 10.1007/BFb0067700 DOI

Kumar LR. Estimation of simultaneous econometric equations using neural networks. System Sciences, 1991 Proceedings of the Twenty-Fourth Annual Hawaii International Conference on. 1991. pp. 124–128.

Kraft K. Are product- and process-innovations independent of each other? Appl Econ. 1990;22: 1029 doi: 10.1080/00036849000000132 DOI

Sheela KG, Deepa SN. Review on methods to fix number of hidden neurons in neural networks. Math Probl Eng. 2013;2013 doi: 10.1155/2013/425740 DOI

Artz KW, Norman PM, Hatfield DE, Cardinal LB. A longitudinal study of the impact of R&D, patents, and product innovation on firm performance. J Prod Innov Manag. 2010;27: 725–740. doi: 10.1111/j.1540-5885.2010.00747.x DOI

Hajek P, Stejskal J. Predicting the innovation activity of chemical firms using an ensemble of decision trees. Proceedings—2015 11th International Conference on Innovations in Information Technology, IIT 2015. 2015. pp. 35–39. doi: 10.1109/INNOVATIONS.2015.7381511 DOI

Zeng X, Yeung DS. Sensitivity analysis of multilayer perceptron to input and weight perturbations. IEEE Trans Neural Networks. 2001;12: 1358–1366. doi: 10.1109/72.963772 PubMed DOI

Yang K-P, Chiao Y-C, Kuo C-C. The relationship between R&D investment and firm profitability under a three-stage sigmoid curve model: evidence from an emerging economy. IEEE Trans Eng Manag. 2010;57: 103–117. doi: 10.1109/TEM.2009.2023452 DOI

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