El índice global de innovación en Colombia: un análisis y selección de los factores influyentes mediante el uso de redes neuronales artificiales

• Julián Alberto Uribe Gómez ^[1]
  1. [1] Instituto Tecnológico Metropolitano

     Instituto Tecnológico Metropolitano

     Colombia

     
• Localización: Contaduría y administración, ISSN 0186-1042, ISSN-e 2448-8410, Vol. 66, Nº. 4, 2021
• Idioma: español
• Títulos paralelos:
  • The global innovation index in Colombia: An analysis and selection of influencing factors through the use of artificial neural networks
• Enlaces
  • Texto completo (pdf)
• Resumen
  • español

    Esta investigación propone un modelo de selección y clasificación para entender cuáles son los factores que impactan en los procesos de innovación para el caso de Colombia. Se analizan los referentes conceptuales sobre el índice global de innovación y la técnica de optimización de redes neuronales artificiales, se presenta el marco de trabajo para el análisis y desarrollo por medio de las redes. Finalmente, se muestran los resultados obtenidos, donde se encuentra que 5 de las 133 variables más importantes para diagnosticar el índice global de innovación son: intensidad en la competencia local, inversión extranjera, crédito, educación terciaria, capital humano e investigación, otras variables descartadas por el modelo como de menor importancia son: PIB por unidad de energía utilizada o cantidad de acciones totales tranzadas. Se espera que los hallazgos sirvan para mejorar el proceso de toma de decisiones en la priorización de marcos de trabajo para los sistemas de innovación regional y nacional.

  • English

    This research proposes a selection and classification model to understand what are the factors that impact innovation processes in the case of Colombia. The conceptual referents on the global innovation index and the technique of artificial neural network optimization are analyzed, the framework for the analysis and development through the networks is presented. Finally, the results obtained are shown, where it is found that 5 of the 133 most important variables to diagnose global innovation index are: intensity in local competition, foreign investment, credit, tertiary education, human capital and research, other variables discarded by the model for its minor importance are: GDP per unit of energy used or amount of total shares traded. The findings are expected to improve the decision-making process in prioritizing frameworks for regional and national innovation systems.

• Referencias bibliográficas
  • Bansal, D. et al. (2018) ‘Comparative Analysis of Various Machine Learning Algorithms for Detecting Dementia’, Procedia Computer Science....
  • Baum, E. B. (1988) ‘On the capabilities of multilayer perceptrons’, Journal of Complexity, 4(3), pp. 193–215. https://doi: 10.1016/0885-064X(88)90020-9.
  • Blanco, A. et al. (2013) ‘Credit scoring models for the microfinance industry using neural networks: Evidence from Peru’, Expert Systems with...
  • Carlsson, B. et al. (2002) ‘Innovation systems : analytical and methodological issues , Research Policy, 31, pp. 233–245.
  • Dalmau, J. et al. (2010) ‘Selecting the Most Relevant Variables for Anaerobic Digestion Imbalances: Two Case Studies’, Water Environment Research,...
  • Devi, S. G. and Sabrigiriraj, M. (2018) ‘Feature Selection, Online Feature Selection Techniques for Big Data Classification: A Review’, Proceedings...
  • Diaz, I. (2019) ‘La innovación en Cuba: un análisis de sus factores clave’, Innovar, 29(71), pp. 43–54. https://doi: 10.15446/innovar.v29n71.76394.
  • Doloreux, D. (2002) ‘What we should know about regional systems of innovation’, Technology in Society, 24(3), pp. 243–263. https://doi: 10.1016/S0160-791X(02)00007-6.
  • Doloreux, D. and Parto, S. (2005) ‘Regional innovation systems: Current discourse and unresolved issues’, Technology in Society, 27(2), pp....
  • Dutta, S. (2017) ‘The Global Innovation Index 2017. Innovation feeding the wold’, (July), pp. 2–30.
  • Ercis, A. and Ünalan, M. (2016) ‘Innovation: A Comparative Case Study of Turkey and South Korea’, Procedia Social and Behavioral Sciences....
  • Farooq, M. et al. (2020) ‘Impact of feature selection algorithm on speech emotion recognition using deep convolutional neural network’, Sensors...
  • Franco, C. and Oliveira, R. H. de (2017) ‘Inputs and outputs of innovation: analysis of the BRICS’, RAI Revista de Administração e Inovação....
  • Geem, Z. W. and Roper, W. E. (2009) ‘Energy demand estimation of South Korea using artificial neural network’, Energy Policy. Elsevier, 37(10),...
  • Hajek, P. and Henriques, R. (2017) ‘Modelling innovation performance of European regions using multi-output neural networks’, PloS one, (October),...
  • Hamadache, M. et al. (2017) ‘Application of multilayer perceptron for prediction of the rat acute toxicity of insecticides’, Energy Procedia....
  • Hanafizadeh, P., Ravasan, A. Z. and Khaki, H. R. (2010) ‘An expert system for perfume selection using artificial neural network’, Expert Systems...
  • Huotari, T., Savolainen, J. and Collan, M. (2020) ‘Deep Reinforcement Learning Agent for S&P 500 Stock Selection’, Axioms, 9(130), pp....
  • Iqbal, R. et al. (2018) ‘Big data analytics: Computational intelligence techniques and application areas’, Technological Forecasting and Social...
  • Jankowska, B., Matysek-Jedrych, A. and Mroczek-dabrowska, K. (2017) ‘Efficiency of National Innovation Systems – Poland and Bulgaria in The...
  • Kengpol, A. and Wangananon, W. (2006) ‘The expert system for assessing customer satisfaction on fragrance notes: Using artificial neural networks’,...
  • Khumprom, P., Grewell, D. and Yodo, N. (2020) ‘for Data-Driven Prognostic Model of Aircraft Engines’.
  • Kigami, J. (2001) ‘Mathematical Background’, in, pp. 196–211. doi: 10.1017/CBO9780511470943.008.
  • Kuzey, C., Uyar, A. and Delen, D. (2014) ‘The impact of multinationality on firm value: A comparative analysis of machine learning techniques’,...
  • Leshno, M. and Spector, Y. (1996) ‘Neural network prediction analysis: The bankruptcy case’, Neurocomputing, 10(2), pp. 125–147. https://doi:...
  • Liu, Y. and Schumann, M. (2005) ‘Data mining feature selection for credit scoring models’, Journal of the Operational Research Society, 56(9),...
  • Mourad, M. et al. (2020) ‘Machine Learning and Feature Selection Applied to SEER Data to Reliably Assess Thyroid Cancer Prognosis’, Scientific...
  • Muller, E., Heraud, J. and Zenker, A. (2017) ‘Are Innovation Systems Complex Systems?’, Springer. https://doi: 10.1007/978-3-319-45901-1.
  • Nair, H., Kumar, A. and Ahmed, O. (2014) ‘Neural network modelling, simulation and prediction of innovation growth in United Arab Emirates...
  • Pençe, I., Kalkan, A. and Çeşmeli, M.Ş . (2019) ‘Estimation of the Country Ranking Scores on the Global Innovation Index 2016 Using the Artificial...
  • Rao, B. C. (2010) ‘How to Measure Innovation’, Challenge, 53(1), pp. 109–125. https://doi: 10.2753/0577-5132530105.
  • Rinkinen, S., Oikarinen, T. and Melkas, H. (2016) ‘Social enterprises in regional innovation systems: a review of Finnish regional strategies’,...
  • Schumpeter, J. (1934) The Theory of Economic Development, Management. Harvard University Press ((trans R. Opie)). https://doi: 10.1007/0-306-48082-4_3.
  • Serrano-Cinca, C. (1996) ‘Self organizing neural networks for financial diagnosis’, Decision Support Systems, 17(3), pp. 227–238. https://doi:...
  • Stuck, J., Broekel, T. and Revilla, J. (2016) ‘Network Structures in Regional Innovation Systems’, European Planning Studies, 24(3), pp. 423–442.
  • Di Tollo, G. et al. (2012) ‘Neural Networks to model the innovativeness perception of co-creative firms’, Expert Systems with Applications....
  • Valdéz, C. and León, J. I. (2015) ‘Hacia una taxonomía de los sistemas regionales de innovación en México’, Economía, Sociedad y Territorio,...
  • Visalakshi, S. and Radha, V. (2015) ‘A literature review of feature selection techniques and applications: Review of feature selection in...
  • West, D. (2000) ‘Neural network credit scoring models’, Computers and Operations Research, 27(11–12), pp. 1131–1152. https://doi: 10.1016/S0305-0548(99)00149-5.
  • Xiang, X. and Deng, Y. (2010) ‘Second order spiking perceptron and its applications’, Applied Mathematical Modelling. Elsevier Inc., 34(10),...
  • Zollo, G., De Crescenzo, E. and Ponsiglione, C. (2011) ‘A gap analysis of regional innovation systems (RIS) with medium-low innovative capabilities:...