Machine learning methods in prospective studies after an example of financing innovation in Colombia

Abstract

The purpose of this article is to make a brief introduction to five advanced machine learning prediction methods which may be useful for the development of prospective studies: logistic regression, support vector machines, gradient powered machines, random forests and neural networks. In addition, it is explained what methodology can be carried out to ensure robustness and validate these prediction models. As an example, it is presented how the use of these methods allowed to identify the most important financial variables to predict the development of innovation activities in Colombian SMEs. The results of the use of these methods may allow generating short and medium-term forecasts that serve to facilitate prospective studies with broader methods, such as the construction of scenarios, with the purpose of generating evidence-based proposals as a roadmap for long-term planning and public policy.

Keywords

logistic regression;, support vector machines;, gradient powered machines;, random forests;, neuronal networks

Author Biography

Ana Milena Padilla-Ospina

Administradora de Empresas, Doctora en Administración

Javier Enrique Medina-Vásquez

Psicólogo, Doctor en Ciencias Sociales

Javier Humberto Ospina-Holguín

Físico, Doctor en Administración

References

Andrews, C. J. (2007). Rationality in policy decision making. En F. Fischer, G. J. Miller, & M. S. Sidney (Eds.), Handbook of public policy analysis: Theory, politics, and methods, 161–171. Boca Ratón, FL: CRC Press.

Banco de la República de Colombia (2017). Salario mínimo legal de Colombia. Recuperado de: http://obiee.banrep.gov.co

Berg, S., Wustmans, M., & Bröring, S. (2019). Identifying first signals of emerging dominance in a technological innovation system: A novel approach based on patents. Technological Forecasting and Social Change, 146 (C), 706–722.

Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.

Carletta, J. (1996). Assessing agreement on classification tasks: The kappa statistic. Computational Linguistics, 22 (2), 249–254.

Cochran, C. E., Mayer, L. C., Carr, T. R., & Cayer, N. J. (2009). American public policy: An introduction. Boston, MA: Cengage Learning.

De Miranda-Santo, M., Coelho, G. M., dos Santos, D. M., & Fellows-Filho, L. (2006). Text mining as a valuable tool in foresight exercises: A study on nanotechnology. Technological Forecasting and Social Change, 73(8), 1013–1027.

EMIS (2017). EMIS. Recuperado de: https://auth.emis.com/module.php/

Fawcett, T. (2004). ROC graphs: Notes and practical considerations for researchers. Machine Learning, 31(1), 1–38.

Frey, D. J. (2011). Policy analysis in practice: Lessons from researching and writing a “statenote” for Education Commission of the States. Capstone Collection, 2425.

Geurts, T. (2011). Public Policy Making: The 21st Century Perspective. Amsterdam: Apeldoom: Beinformed.

Gu, S., Kelly, B., & Xiu, D. (2018). Empirical asset pricing via machine learning (No. w25398). National Bureau of Economic Research.

Ho, R. (2012). Big data machine learning: Patterns for predictive analytics. DZone Refcardz, 2014. Recuperado de: http://refcardz.dzone.com/refcardz/machine-learning-predictive

Jeong, Y., Park, I., & Yoon, B. (2019). Identifying emerging Research and Business Development (R&BD) areas based on topic modeling and visualization with intellectual property right data. Technological Forecasting and Social Change, 146, 655–672.
Kim, J., Hwang, M., Jeong, D.-H., & Jung, H. (2012). Technology trends analysis and forecasting application based on decision tree and statistical feature analysis. Expert Systems with Applications, 39 (16), 12618–12625.

Kose, T., & Sakata, I. (2018). Analysis of technology convergence in robotics and technological portfolios among robot-related organizations. 2018 Portland International Conference on Management of Engineering and Technology (PICMET), 1–12. IEEE.

Kuhn, M., & Johnson, K. (2013). Applied predictive modeling. New York: Springer.

Kwakkel, J. H., & Pruyt, E. (2013). Exploratory Modeling and Analysis, an approach for model-based foresight under deep uncertainty. Technological Forecasting and Social Change, 80(3), 419–431.

Landis, J. R., & Koch, G. G. (1977). The measurement of observer agreement for categorical data. Biometrics, 33(1), 159–174.

Lee, C., Kwon, O., Kim, M., & Kwon, D. (2018). Early identification of emerging technologies: A machine learning approach using multiple patent indicators. Technological Forecasting and Social Change, 127, 291–303.

Ley 905. (2004). Por medio de la cual se modifica la Ley 590 de 2000 sobre promoción del desarrollo de las micro, pequeña y mediana empresa Colombiana y se dictan otras disposiciones. Colombia: Congreso de la República de Colombia.

Ma, J., Abrams, N. F., Porter, A. L., Zhu, D., & Farrell, D. (2019). Identifying translational indicators and technology opportunities for nanomedical research using tech mining: The case of gold nanostructures. Technological Forecasting and Social Change, 146, 767–775.

Malakar, G. (2018). Introduction to Gradient Boosting algorithm. Recuperado de: https://youtu.be/ERDgauqhTHk

Mandrekar, J. N. (2010). Receiver operating characteristic curve in diagnostic test assessment. Journal of Thoracic Oncology, 5 (9), 1315–1316.

Manning, C., Raghavan, P., & Schütze, H. (2010). Introduction to information retrieval. Natural Language Engineering, 16 (1), 100–103.

Medina-Vásquez, J. E., Becerra, S., & Castaño, P. (2014). Prospectiva y política pública para el cambio estructural en América Latina y el Caribe. Santiago de Chile: CEPAL.

Yang, K., & Miller, G. J. (2007). Handbook of Research Methods in Public Administration. Boca Ratón: CRC Press.

Moerhle, M. G., & Caferoglu, H. (2019). Technological speciation as a source for emerging technologies. Using semantic patent analysis for the case of camera technology. Technological Forecasting and Social Change, 146, 776–784.

Olson, D. L., & Delen, D. (2008). Advanced data mining techniques. Berlin: Springer.

Popper, R. (2008). How are foresight methods selected? Foresight, 10(6), 62–89.

Porter, A. L., Garner, J., Carley, S. F., & Newman, N. C. (2019). Emergence scoring to identify frontier R&D topics and key players. Technological Forecasting and Social Change, 146, 628–643.

Simon, H. A. (1976). Administrative Behavior: A Study of Decision-Making Processes in Administrative Organization. Nueva York: Harper & Rowe.

Sokolova, M., Japkowicz, N., & Szpakowicz, S. (2006). Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. Proceedings of the ACS Australian joint conference on artificial intelligence, 1015–1021. Berlín: Springer.

Sydney, M. S. (2007). Policy formulation: Design and tools. In F. Fischer, G. J. Miller., & M. S. Sidney (Eds.), Handbook of public policy analysis: Theory, politics, and methods 79–88. Boca Ratón, FL: CRC Press.

Vapnik, V. (2000). The nature of statistical learning theory (2a Ed.). New York: Springer.

Wang, Z., Porter, A. L., Wang, X., & Carley, S. (2019). An approach to identify emergent topics of technological convergence: A case study for 3D printing. Technological Forecasting and Social Change, 146, 723–732.

Wittmer, D. P., & McGowan, R. P. (2007). Five conceptual tools for decision-making. En Jack Rabin, W. B. Hildreth, & G. J. Miller (Eds.), Handbook of Public Administration 315–342. Boca Ratón, FL: CRC Press.

Yang, K. (2007). Quantitative methods for policy analysis. En J. Rabin, B. Hildreth, & G. J. Miller (Eds.), Handbook of Public Policy Analysis: Theory, Politics, and Methods 349–367. Boca Ratón: CRC Press.

Zhang, Y., Porter, A., Chiavetta, D., Newman, N. C., & Guo, Y. (2019). Forecasting technical emergence: An introduction. Technological Forecasting and Social Change, 146, 626–627.