Türkiye’de Girişimcilik ve Sürdürülebilir Bölgesel Kalkınma: Makine Öğrenmesi Yaklaşımlarından Elde Edilen Bulgular

Year 2021, , 882 - 911, 30.12.2021

Ebru Tomris Aydoğan , Esra Karadeniz , Mehmet Güney Celbiş

https://doi.org/10.30784/epfad.961838

Abstract

Birleşmiş Milletler Kalkınma Programı (UNDP), Sürdürülebilir Kalkınma’nın (SK) sağlanmasında girişimciliği önemli bir faktör olarak tanımlamaktadır. Bu çalışmanın amacı, sosyal bilimlerde nispeten yeni bir yöntem olan makine öğrenmesini uygulayarak ve Küresel Girişimcilik Monitörü (GEM) verilerini kullanarak Türkiye'deki girişimcilik faaliyetlerini SK açısından etkileyen faktörleri analiz etmektir. Rassal Orman model bulgularına göre çalışma durumu, başka bir girişimci tanımak, kişinin kendi bilgisi ve becerisi hakkındaki görüşü, ihtiyaç/mecburiyet ve yaş, girişimci olmak için önemli faktörlerdir. Ayrıca, hanehalkı geliri ve nüfusu, kişinin çalışma durumu, cinsiyeti, eğitim düzeyi ve anket zamanı itibariyle şirket içi girişimcilik aktivitesinde bulunması da önemli faktörler olarak tespit edilmişlerdir. Stokastik Gradyan Artırma sonuçlarına göre Türkiye’de bölgesel kalkınmanın ve koşulların bireylerin girişimci olma olasılıklarını etkilediği gözlenmiştir. Bu araştırma, Özdemir ve Karadeniz (2011) ile Karadeniz ve Özçam'ın (2018) Türkiye bağlamında bireysel girişimci kazanımlarından buldukları önceki sonuçları ilk kez makine öğrenmesi algoritmaları uygulaması aracılığıyla analiz etmekte ve genişletmektedir. Girişimcilik faaliyetleri sürdürülebilir kalkınmayı destekleyen politikalar çerçevesinde planlanmalıdır.

Keywords

Ekonomik Kalkınma, Girişimcilik, Bölgesel Analiz, Makine Öğrenmesi

Entrepreneurship and Sustainable Regional Development in Turkey: Findings Obtained from Machine Learning Approaches

Abstract

The United Nations Development Programme (UNDP) defines entrepreneurship as an important factor in achieving Sustainable Development (SD). The aim of this study is to analyze the factors affecting entrepreneurship activities in Turkey in terms of SD by applying machine learning, which is a relatively new method in social sciences, and using Global Entrepreneurship Monitor (GEM) data. According to the results of the Random Forest model, working status, knowing another entrepreneur, one’s opinion about one’s own knowledge and skills, need/obligation and age are important factors for being an entrepreneur. Also, household income and population, the employment status, gender, education level, and the engagement in intra-company entrepreneurial activity of the person at the time of the survey were also determined as important factors. According to the results of the Stochastic Gradient Boosting, it is observed that regional development and conditions in Turkey affect the probability of individuals to become entrepreneurs. This research analyzes and extends the previous results of Özdemir and Karadeniz (2011) and Karadeniz and Özçam (2018) from individual entrepreneur gains in the Turkish context for the first time through the application of machine learning algorithms. Entrepreneurial activities should be planned within the framework of policies that support sustainable development.

Keywords

Economic Development, Entrepreneurship, Regional Analysis, Machine Learning

References

• Aldrich, C. and Auret, L. (2013). Unsupervised process monitoring and fault diagnosis with machine learning methods. London: Springer.
• Alpaydın, E. (2016). Machine learning: The new AI. Cambridge: MIT Press.
• Arenius, P. and Minniti, M. (2005). Perceptual variables and nascent entrepreneurship. Small Business Economics, 24(3), 233-247. doi:10.1007/s11187-005-1984-x
• Athey, S. and Imbens, G. W. (2019). Machine learning methods that economists should know about. Annual Review of Economics, 11, 685-725. https://doi.org/10.1146/annurev-economics-080217-053433
• Avrupa Komisyonu. (2019). Female entrepreneurs. Retrieved from https://ec.europa.eu/growth/smes/promoting-entrepreneurship/we-work-for/women_en
• Birleşmiş Milletler Genel Kurulu. (2016). Sürdürülebilir kalkınma için girişimcilik: Genel kurul tarafından kabul edilen karar. Erişim adresi: https://digitallibrary.un.org/record/855166
• Bosma N., Hill, S., Ionescu-Somers, A., Kelley D., Levie, J. and Tarnawa, A. (2020). Entrepreneurship monitor 2019/2020 global report. Retrieved from https://www.babson.edu/media/babson/assets/global-entrepreneurship-monitor/2019-2020-GEM-Global-Report.pdf
• Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123-140. https://doi.org/10.1007/BF00058655
• Breiman, L. (2001a). Random forests. Machine Learning, 45(1), 5-32. https://doi.org/10.1023/A:1010933404324
• Breiman, L. (2001b). Statistical modeling: The two cultures (with comments and a rejoinder by the author). Statististical Science, 16(3), 199-231. doi:10.1214/ss/1009213726
• Breiman, L. and Cutler, A. (2021). Random forests. Retrieved from https://www.stat.berkeley.edu/~breiman/RandomForests/
• Breiman, L., Friedman, J. H., Olshen, R. A. and Stone, C. J. (1984). Classification and regression trees. Monterey, CA: Wadsworth and Brooks.
• Carr, L. T. (1994). The strenghts and weaknesses of quantitative and qualitative research: What method for nursing? Journal of Advanced Nursing, 20(4), 716-721. https://doi.org/10.1046/j.1365-2648.1994.20040716.x
• Celbiş, M. G. (2021). A machine learning approach to rural entrepreneurship. Papers in Regional Science, 100(4), 1079-1104. https://doi.org/10.1111/pirs.12595
• Cetindamar, D., Gupta, V. K., Karadeniz, E. E. and Egrican, N. (2012). What the numbers tell: The impact of human, family and financial capital on women and men's entry into entrepreneurship in Turkey. Entrepreneurship & Regional Development, 24(1-2), 29-51. https://doi.org/10.1080/08985626.2012.637348
• Department of Economic and Social Affairs. (2015). Sustainable development. Retrieved from https://sdgs.un.org/
• Filser, M., Kraus, S., Roig-Tierno, N., Kailer, N. and Fischer, U. (2019). Entrepreneurship as catalyst for sustainable development: Opening the black box. Sustainability, 11(16), 4503. https://doi.org/10.3390/su11164503
• Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 5, 1189-1232. doi:10.1214/aos/1013203451
• Friedman, J. H. (2002). Stochastic gradient boosting. Computational Statistics and Data Analysis, 38(4), 367-378. https://doi.org/10.1016/S0167-9473(01)00065-2
• Friedman, J., Hastie, T. and Tibshirani, R. (2001). The elements of statistical learning. Berlin: Springer.
• Géron, A. (2019). Hands-on machine learning with scikit-learn, keras, and tensorflow: Concepts, tools, and techniques to build intelligent systems. USA: O’Reilly Media, Inc.
• Global Entrepreneurship Monitor. (2018). The World's foremost study of entrepreneurship. Retrieved from www.gemconsortium.org
• Goldstein, A., Kapelner, A., Bleich, J. and Pitkin, E. (2015). Peeking inside the black box: Visualizing statistical learning with plots of individual conditional expectation. Journal of Computational and Graphical Statistics, 24(1), 44-65. Retrieved from http://www.jstor.org/
• Hersh, J. and Harding, M. (2018). Big data in economics. IZA World of Labor, (451). doi:10.15185/izawol.451
• Imbens, G. and Athey, S. (2021). Breiman’s two cultures: A perspective from econometrics. Observational Studies, 7(1), 127-133. doi:10.1353/obs.2021.0028
• James, G., Witten, D., Hastie, T. and Tibshirani, R. (2013). An introduction to statistical learning. New York: Springer.
• Karadeniz, E. E. and Özçam, A. (2018). Regional disparities in entrepreneurship in Turkey with respect to gender using a regression of pooling cross sections: 2006-2015. In N. Faghih and M. R. Zali (Eds.), Entrepreneurship in the Middle East and North Africa (MENA). New York: Springer. https://doi.org/10.1007/978-3-319-75913-5
• Kim, P. H., Aldrich, H. E. and Keister, L. A. (2006). The impact of financial, human, and cultural capital on entrepreneurial entry in the United States. Small Business Economics, 27, 5-22. https://doi.org/10.1007/s11187-006-0007-x
• Kuhn, M. (2008). Building predictive models in R using the caret package. Journal of Statistical Software, 28(5), 1-26. Doi: 10.18637/jss.v028.i05
• Liaw, A. ve Wiener, M. (2002). Classification and regression by randomforest. R News. 2(3), 18-22. Retrieved from https://cogns.northwestern.edu/cbmg/LiawAndWiener2002.pdf
• Mullainathan, S. and Spiess, J. (2017). Machine learning: An applied econometric approach. Journal of Economic Perspectives, 31(2), 87-106. doi:10.1257/jep.31.2.87
• Organization of Economic Cooperation and Development. (2020). OECD regions and cities at a glance 2020. Retrieved from https://www.oecd.org/regional/oecd-regions-and-cities-at-a-glance-26173212.htm
• Özçam, A. and Karadeniz, E. (2018). How did women entrepreneurship change over time in Turkey (2006-2015): A regression of pooling cross sections across time. Contemporary Research in Economics and Social Sciences, 2(1), 43-69. Retrieved from https://dergipark.org.tr/en/pub/conress/
• Özdemir, Ö. and Karadeniz, E. E. (2009). Differences between being an opportunity-driven and necessity-driven entrepreneur: Evidence from Turkey’s GEM data. Paper presented at the 4th European Conference on Entrepreneurship and Innovation. University of Antwerp, Belgium. Retrived from https://avesis.metu.edu.tr/yayin/e7b50ba9-31c0-4d2d-bbfb-b6b4c6857442/differences-between-being-opportunity-driven-and-necessity-driven-entrepreneur-evidence-from-turkeys-gem-data
• Özdemir, Ö. and Karadeniz, E. E. (2011). Investigating the factors affecting total entrepreneurial activities in Turkey. METU Studies in Development, 38, 275-290. Retrieved from http://www2.feas.metu.edu.tr/metusd/ojs/
• Özgüzel, C. (2020). Agglomeration effects in a developing economy: Evidence from Turkey (PSE Working Papers No. 1341). Retrieved from https://erf.org.eg/app/uploads/2019/09/1341.pdf
• Ployhart, R. E. and Moliterno, T. P. (2011). Emergence of the human capital resource: A multilevel model. Academy of Management Review, 36(1), 127-150. https://doi.org/10.5465/AMR.2011.55662569
• Reynolds, P. D., Hay, M., Bygrave, W. D., Camp, S. M. and Autio, E. (2000). Global entrepreneurship monitor: 2000 executive report. MO: Kauffman Foundation Kansas.
• Santos, S. C., Caetano, A., Spagnoli, P., Fernandes Costa, S. and Neumeyer, X. (2017). Predictors of entrepreneurial activity before and during the European economic crisis. The International Entrepreneurship and Management Journal, 13(4), 1263-1288. doi:10.1007/s11365-017-0453-8
• Siffert, P. V. and Guimarães, L. D. O. (2020). Entrepreneurial ecosystem and sustainability as catalysts for regional development: Proposition of a theoretical framework. Interações (Campo Grande), 21, 739-752. http://dx.doi.org/10.20435/inter.v21i4.2647
• Sutton, C. D. (2005). Classification and regression trees, bagging, and boosting. Handbook of Statistics, 24, 303-329. https://doi.org/10.1016/S0169-7161(04)24011-1
• Türk, U. (2020). Gelir dağılımında fırsat eşitsizliği ve alt kırılımları: Türkiye üzerine bir araştırma. Alternatif Politika, 12(2), 311-335. Erişim adresi: https://alternatifpolitika.com
• United Nations Development Program. (2021). Sürdürülebilir kalkınma amaçları. Erişim adresi: https://www.undp.org/sustainable-development-goals
• Verheul, I., Wennekers, S., Audretsch, D. and Thurik, R. (2001). An eclectic theory of entrepreneurship: Policies, institutions, and culture (Tinbergen Institute No. 030/3). Retrieved from https://papers.tinbergen.nl/01030.pdf
• Vodã, A. I., Butnaru, G. I. and Butnaru, R. C. (2020). Enablers of entrepreneurial activity across the European Union: An analysis using GEM individual data. Sustainability, 12(3), 1022. https://doi.org/10.3390/su12031022
• Wennekers, S., van Stel, A., Thurik, R. and Reynolds, P. (2005). Nascent entrepreneurship and the level of economic development. Small Business Economics, 24, 293-309. https://doi.org/10.1007/s11187-005-1994-8