The Backstage of the Doing Business Index and the Logistic Performance Index: A Machine Learning Analysis

Abstract

Globalization has significantly boosted foreign commerce, enhancing the flow of capital, information, goods, and services between nations, thereby influencing countries' positions in the industrial market and offering growth opportunities. Concurrently, the mobility of investment capital and entrepreneurs has increased, prompting countries to innovate to attract investors. Investors, aiming to sustain their global market presence and profitability, often establish businesses in various countries. To assess the investment environment, indices like the Doing Business Index (DBI) and the Logistics Performance Index (LPI) by the World Bank are crucial references. This study focuses on analyzing the factors affecting DBI and LPI using machine learning algorithms (CatBoost, LightGBM, and XGBoost) on 1478 variables from the World Development Indicators (WDI). The analysis identified the top 20 factors influencing DBI and LPI, highlighting the significance of economic, administrative, legal indicators, and technological infrastructure. The findings provide valuable insights for countries aiming to improve their DBI and LPI scores and for investors seeking critical factors beyond these indices, contributing significantly to both the business world and academic literature.

Keywords

• Doing Business Index
• Logistic Performance Index
• CatBoost
• LightGBM
• XGBoost
• Machine Learning

References

1. Acar, Ö. F., & Çetinceli, K. (2020). Uluslararası ticarette taşıma türlerinin Türkiye'nin lojistik performans endeksine etkisi ve iş yapma kolaylığı endeksi ilişkisi. Mehmet Akif Ersoy Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 7(3), 887-905. https://doi.org/10.30798/makuiibf.796320
2. Aghion, P. (2004). Growth and development: A Schumpeterian approach. Annals of Economics and Finance, 5, 1-25.
3. Akame, A. J., Ekwelle, M. E., & Njei, G. N. (2016). The impact of business climate on foreign direct investment in the CEMAC region. Journal of Economics and Sustainable Development, 7(22), 66–74.
4. Altınok, N. (2022). Makina öğrenmesi teknikleri ile hukuki alacak tahsilat kuruluşu dosya kapatılabilirlik tahmini ve atama modeli ile dosya ataması: Telekomünikasyon sektörü örneği (Yüksek lisans tezi). İstanbul Teknik Üniversitesi.
5. Ani, T. G. (2015). Effect of ease of doing business to economic growth among selected countries in Asia. Asia Pacific Journal of Multidisciplinary Research, 3(5), 139-145.
6. Aynagöz Çakmak, Ö. (2016). WTO-ticareti kolaylaştırma anlaşması ve Türkiye için değerlendirmeler. Afyon Kocatepe Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 18(1), 1–13.
7. Babayigit, B., Gürbüz, F., & Denizhan, B. (2023). Logistics performance index estimating with artificial intelligence. International Journal of Shipping and Transport Logistics, 16(3-4), 360-371. https://doi.org/10.1504/IJSTL.2023.129876
8. Bakmaz, O., Dragosavac, M., Popović, D., Brakus, A., Pajović, I., Turčinović, Ž., & Popović, S. (2024). The significance of real financial reporting of agricultural mechanism in relation to the making of management decisions of individual farms and medium-sized agricultural enterprises. Poljoprivreda i Sumarstvo, 70(1), 171-184. https://doi.org/10.17707/AgricultForest.70.1.12

9. Başar, S. İ., & Bozma, G. (2017). Ülkelerin lojistik performanslarının belirleyicileri. Kafkas Üniversitesi Sosyal Bilimler Enstitüsü, 20, 447-458.
10. Bayraktar, N. (2015). Importance of investment climates for inflows of foreign direct investment in developing countries. Business and Economic Research, 5(1), 24–50. http://doi.org/10.5296/ber.v5i1.6762
11. Bayraktutan, Y., & Özbilgin, M. (2015). Lojistik maliyetler ve lojistik performans ölçütleri. Maliye Araştırmaları Dergisi, 1(2), 95-112.
12. Bozma, G., Başar, S. İ., & Aydın, S. (2017). Lojistik performansının ekonomik büyüme üzerindeki etkisi. The International New Issues in Social Sciences, 5(5), 401-414.
13. Brownlee, J. (2016). XGBoost with python: Gradient boosted trees with XGBoost and scikit-learn, Machine Learning Mastery.
14. Bruhn, M. (2011). License to sell: The effect of business registration reform on entrepreneurial activity in Mexico. The Review of Economics and Statistics, 93(1), 382-386. https://doi.org/10.1596/1813-9450-4538
15. Burmaoglu, S., & Sesen, H. (2011). Analyzing the dependency between national logistics performance and competitiveness: Which logistics competence is core for national strategy? Journal of Competitiveness, 3(4), 4-22.
16. Cavusgil, S. T., Kiyak, T., & Yeniyurt, S. (2004). Complementary approaches to preliminary foreign market opportunity assessment: Country clustering and country ranking. Industrial Marketing Management, 33(7), 607-617. https://doi.org/10.1016/j.indmarman.2003.10.005
17. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). USA. https://doi.org/10.1145/2939672.2939785
18. Çitil, M. (2022). Yeşil lojistik ve lojistik performans ile yönetişim kalitesi arasındaki ilişkiye yönelik bir inceleme. Dicle Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 12(24), 322-352. https://doi.org/10.53092/duiibfd.1133548
19. Dorogush, A. V., Ershov, V., & Gulin, A. (2018). CatBoost: Gradient boosting with categorical features support. ArXiv preprint. ArXiv:1810.11363.
20. Doshi, R., Kelley, J. G., & Simmons, B. A. (2019). The power of ranking: The ease of doing business indicator and global regulatory behavior. International Organization, 73(3), 611-643. http://doi.org/10.1017/S0020818319000158
21. Dougherty, S. (2007). China and India: Making sense of innovation and growth. OECD Observer, (264-265), 60–61.
22. Eifert, P. B. (2009). Do regulatory reforms stimulate investment and growth? Evidence from the doing business data, 2003-07. Centre for Global Development, 159, 1-47. http://doi.org/10.2139/ssrn.1390326
23. Feng, P., Zhou, X., Zhang, D., Chen, Z., & Wang, S. (2022). The impact of trade policy on global supply chain network equilibrium: A new perspective of product market chain competition. Omega, 109, 102612. https://doi.org/10.1016/j.omega.2022.102612
24. Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189-1232.
25. Garcia, C., & Hinayon, D. (2018). Components of ease of doing business inferred from macroeconomic performance indicators. Journal of Educational and Human Resource Development (JEHRD), 6, 161-171.
26. Haggard, D. L., & Haggard, K. S. (2018). The impact of law, religion, and culture on the ease of starting a business. International Journal of Organization Theory & Behavior, 21(4), 242-257. https://doi.org/10.1108/IJOTB-04-2018-0043
27. Holden, P., & Pekmezovic, A. (2020). How accurate are the doing business indicators? A Pacific Island case study. Asia & the Pacific Policy Studies, 7(3), 247-261. https://doi.org/10.1002/app5.313
28. Kara, M., Tayfur, L., & Basık, H. (2009). Küresel ticarette lojistik üslerin önemi ve Türkiye. Mustafa Kemal Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 6(11), 69-84.
29. Kaya Samut, P. (2023). OECD ülkelerinin yeşil lojistik performansı ile enerji, sağlık ekonomisi ve çevre ilişkisinin analizi. Verimlilik Dergisi, Döngüsel Ekonomi ve Sürdürülebilirlik Özel Sayısı, 67-83. https://doi.org/10.51551/verimlilik.1112577
30. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., & Liu, T. Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, 30, 3146-3154.
31. Klapper, L., Laeven, L., & Rajan, R. (2004). Business environment and firm entry: Evidence from international data. Washington, DC: World Bank Publications.
32. Koç, E., Kaya, K., & Şenel, M. C. (2017). Dünya’da ve Türkiye’de ekonomik göstergeler-iş yapma/iş kurma kolaylığı endeksi. Mühendis ve Makine, 58(685), 17-42.
33. Kumar, P., & Kumar, D. (2020). Ease of doing business: A critical overview. Aegaeum Journal, 8(9), 587-598.
34. Maričić, M., Bulajic, M., Radojicic, Z., & Jeremic, V. (2019). Shedding light on the doing business index: A machine learning approach. Business Systems Research Journal, 10(2), 73-84. https://doi.org/10.2478/bsrj-2019-019
35. Martí, L., Puertas, R., & Garcia, L. (2014). The importance of the logistics performance index in international trade. Applied Economics, 46(24), 2982-2992. https://doi.org/10.1080/00036846.2014.916394
36. Mengistu, A. (2015). The nexus between governance infrastructure and the ease of doing business in Africa. In O. D. Joseph & B. O. A. Kwame (Eds.), Comparative case studies on entrepreneurship in developed and developing countries (pp. 110–131). Hershey, PA: IGI Global. http://doi.org/10.4018/978-1-4666-7533-9.ch007
37. Meşin, K., & Cura, F. (2022). Türkiye dış ticaretinin lojistik performans çerçevesinde değerlendirilmesi. Sosyal Ekonomik Araştırmalar Dergisi, 22(2), 139–149. https://doi.org/10.30976/susead.1148908
38. Mete, E. (2020). Sürdürülebilir kalkınma kapsamında yeşil lojistik: Avrupa Birliği ve Türkiye örneği. Karadeniz Sosyal Bilimler Dergisi, 12(23), 383-396. https://doi.org/10.38155/ksbd.790740
39. Natekin, A., & Knoll, A. (2013). Gradient boosting machines, a tutorial. Frontiers in Neurorotics, 7(21), 1-21. https://doi.org/10.3389/fnbot.2013.00021
40. Ofluoğlu, N. Ö., Kalaycı, C., Artan, S., & Bal, H. Ç. (2018). Lojistik performansındaki gelişmelerin uluslararası ticaret üzerindeki etkileri: AB ve MENA ülkeleri örneği. Gümüşhane Üniversitesi Sosyal Bilimler Dergisi, 9(24), 92-109.
41. Ojala, L., & Queiroz, C. (2002). Logistics friendliness, GDP and the perceived level of corruption of countries. In Proceedings of the LRN Conference (pp. 211–216). Birmingham, UK: The Institute of Logistics and Transport.
42. Olival, A. I. D. N. (2012). The influence of Doing Business’ institutional variables in foreign direct investment (Master’s thesis). Universidade Católica Portuguesa.
43. Önalmış, Ç. (2017). İş yapma kolaylığı kriterleri ile ülke sıralamaları: SMAA yöntemleri ile bir uygulama (Yüksek lisans tezi). Hacettepe Üniversitesi.
44. Pala, O. (2022). İş yapma kolaylığı açısından ülkelerin performanslarının karşılaştırılması: Türkiye ve Vişegrad örneği. Akademik Araştırmalar ve Çalışmalar Dergisi (AKAD), 14(27), 411-422. https://doi.org/10.20990/kilisiibfakademik.1147201
45. Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., & Gulin, A. (2018). CatBoost: Unbiased boosting with categorical features. In Proceedings of the 32nd Conference on Neural Information Processing Systems (NeurIPS 2018) (pp. 1–11). Montréal, Canada.
46. Rençber, Ö. F., & Yücekaya, P. (2021). Girişimcilerin yabancı ülkelere yatırım kararları açısından iş yapma kolaylığını etkileyen faktörler üzerine bir araştırma. European Journal of Managerial Research (EUJMR), 5(Özel Sayı 1), 206-220.
47. Sanjeetha, R., Ra, A., Kolli, S., Irteqa, A. M., B, S., & Anita, K. (2021). Detection and mitigation of botnet based DDoS attacks using CatBoost machine learning algorithm in SDN environment. International Journal of Advanced Technology and Engineering Exploration, 8, 445-461.
48. Shepherd, B., & Sriklay, T. (2023). Extending and understanding: an application of machine learning to the World Bank's logistics performance index. International Journal of Physical Distribution & Logistics Management, 53(9), 985-1014. https://doi.org/10.1108/IJPDLM-06-2022-0180
49. Sofyalıoğlu, Ç., & Kartal, B. (2013). Türkiye ve Avrasya Ekonomik Topluluğu ülkelerinin lojistik performans indekslerinin karşılaştırılması ve bazı çıkarımlar. In Proceedings of the International Conference on Eurasian Economies (pp. 524–531). St. Petersburg, Russia.
50. Tekin, A. T., & Sarı, C. (2022). Mağaza tabanlı talep tahmini: Topluluk öğrenmesi yaklaşımları ile zaman serisi yaklaşımı karşılaştırılması. In Proceedings of the International Engineering and Technology Management Summit 2022 (ETMS 2022) (pp. 225–230). İstanbul, Türkiye.
51. Toh, K. T. K., Nagel, P., & Oakden, R. (2009). A business and ICT architecture for a logistics city. International Journal of Production Economics, 122(1), 216-228.
52. Wood, D. F., Barone, A., Murphy, P., & Wardlow, D. L. (1995). International logistics. London: Chapman & Hall.
53. World Bank. (2015). Doing Business 2016: Measuring regulatory quality and efficiency. Washington, DC: World Bank Publications. Retrieved August 14, 2023, from https://www.proquest.com/legacydocview/EBC/4397383?accountid=15958
54. World Bank. (2023). The logistics performance index and its indicators. Retrieved August 19, 2023, from https://lpi.worldbank.org/sites/default/files/2023-04/LPI_2023_report_with_layout.pdf
55. World Bank. (2024a). Metadata glossary. Retrieved August 22, 2024, from https://databank.worldbank.org/metadataglossary/world-development-indicators/series/IC.BUS.DISC.XQ
56. World Bank. (2024b). Metadata glossary. Retrieved August 22, 2024, from https://databank.worldbank.org/metadataglossary/worldwide-governance-indicators/series/RQ.PER.RNK.LOWER
57. Yalçın, A., & Yalçın, S. (2021). İş yapma kolaylığı endeksi kapsamında Nijerya’nın performans performans analizi. AHBV Akdeniz Havzası ve Afrika Medeniyetleri Dergisi, 3(1), 9-22.
58. Yardımcıoğlu, M. (2015). Yükselen piyasa ekonomileri ve iş yapabilirlik endeksi karşılaştırması. Kahramanmaraş Sütçü İmam Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi, 4(1), 279-294.