CLASSIFICATION THE USE OF E-COMMERCE IN TURKEY WITH MACHINE LEARNING AND ANALYZING ITS RELATIONSHIP WITH VARIOUS VARIABLES

Öz

In this study, the classification of e-commerce usage status with machine learning methods was carried out using the Household Information Technology Usage Survey data conducted by the Turkish Statistical Institute in 2023. In addition, demographic factors such as gender, age, education level, technology usage status and social media usage were analyzed in relation to e-commerce usage. This data set was analyzed using decision trees, one of the data mining classification techniques. In the study, various machine learning models such as Random Forest, Nearest Neighbors, Support Vector Machine, Logistic Regression, Naive Bayes and Gradient Boosting were used for classification. The results of the analysis showed that the Gradient Boosting model is a powerful tool for classifying e-commerce usage, especially notable for its high accuracy rate. The study also suggests strategies for improving e-commerce usage.

Anahtar Kelimeler

• E-commerce
• Household Information Technologies
• Machine Learning
• Classification Techniques
• Data Mining

Türkiye'de E-Ticaretin Kullanılma Durumunun Makine Öğrenmesi İle Sınıflandırılması ve Çeşitli Değişkenlerle İlişkilerinin Analizi

Öz

Bu çalışmada, Türkiye İstatistik Kurumu’nun (TÜİK) 2023 yılında gerçekleştirdiği Hanehalkı Bilişim Teknolojileri Kullanımı Araştırması (HBTKA) verileri kullanılarak, e-ticaret kullanım durumunun makine öğrenmesi yöntemleri ile sınıflandırılma işlemi gerçekleştirilmiştir. Bununla birlikte, cinsiyet, yaş, eğitim durumu gibi demografik faktörler ile teknoloji kullanım durumu ve sosyal medya kullanımı gibi faktörlerin e-ticaret kullanımı ile ilişkileri analiz edilmiştir. Bu veri seti üzerinde, veri madenciliği sınıflandırma tekniklerinden karar ağaçları kullanılarak analiz yapılmıştır. Çalışmada, sınıflandırma işlemi için Rastgele Orman, En Yakın Komşular, Destek Vektör Makinesi, Lojistik Regresyon, Naive Bayes ve Gradient Boosting gibi çeşitli makine öğrenmesi modelleri kullanılmıştır. Analiz sonuçları, özellikle Gradient Boosting modelinin yüksek doğruluk oranıyla dikkat çekerek, e-ticaret kullanımının sınıflandırılmasında güçlü bir araç olduğunu göstermiştir. Çalışmada ayrıca, e-ticaret kullanımının iyileştirilmesine yönelik stratejiler önerilmektedir.

Anahtar Kelimeler

• E-ticaret
• Hanehalkı Bilişim Teknolojileri
• Makine Öğrenmesi
• Sınıflandırma Teknikleri
• Veri Madenciliği.

Kaynakça

1. Agarwal, G. and Sun, Y. (2020). Bivariate functional quantile envelopes with application to radiosonde wind data. Technometrics, 63(2), 199-211. https://doi.org/10.1080/00401706.2020.1769734
2. Ahmed, M. (2023). Understanding the artificial intelligence implementation for allocating an order to a seller among multiple sellers who sell the same product.. https://doi.org/10.5772/intechopen.105560
3. Alkan, Ö., Abar, H. ve Karaaslan, A. (2015). Hanelerde Bulunan Bilişim Ekipmanları Sayısını Etkileyen Faktörlerin Poisson Regresyon Modeliyle Araştırılması. Atatürk Üniversitesi 2. Ulusal Yönetim Bilişim Sistemleri Kongresi, Erzurum.
4. Alkan, Ö., Küçükoglu, H., ve Tutar, G. (2021). Modeling of the factors affecting e-commerce use in turkey by categorical data analysis. International Journal of Advanced Computer Science and Applications, 12(1). https://doi.org/10.14569/ijacsa.2021.0120113
5. Aslanbay, Y., Aslanbay, M. ve Çobanoğlu, E. (2009). Internet addiction among turkish young consumers. Young Consumers, 10(1), 60-70. https://doi.org/10.1108/17473610910940792
6. Cao, X., Stojković, I., ve Obradović, Z. (2016). A robust data scaling algorithm to improve classification accuracies in biomedical data. BMC Bioinformatics, 17(1). https://doi.org/10.1186/s12859-016-1236-x
7. Coelho, T., Mossotto, E., Gao, Y., Haggarty, R., Ashton, J. J., Batra, A., … ve Ennis, S. (2020). Immunological profiling of paediatric inflammatory bowel disease using unsupervised machine learning. Journal of Pediatric Gastroenterology and Nutrition, 70(6), 833-840. https://doi.org/10.1097/mpg.0000000000002719
8. Cortes, C. ve Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273-297. https://doi.org/10.1007/bf00994018

9. Coşkun, M. ve Bülbül, H. İ. (2019). Hanehalkı Bilişim Teknolojileri Kullanımının Veri Madenciliği Teknikleri ile Analizi. TÜBAV Bilim Dergisi, 12(2), 1-17.
10. Dalgic-Tetikol, D. E., Guloglu, B., ve Köksal, E. (2022). Determinants of internet adoption in Turkey and the need for a more coherent vision on information and communication technologies policy. Competition and Regulation in Network Industries, 23(4), 311-336. https://doi.org/10.1177/17835917221143060
11. Durmaz, Y. ve Dağ, K. (2021). Consumption, consumer behavior and new habits acquired by consumers as a result of covid-19 measures. International Journal of Research, 9(7), 318-328. https://doi.org/10.29121/granthaalayah.v9.i7.2021.4111
12. Fernando, N., Mery, M., Jessica, J., ve Andry, J. F. (2020). Utilization of big data in e-commerce business. Conference Series, 3(1), 62-67. https://doi.org/10.34306/conferenceseries.v3i1.383
13. Fuentes-Hurtado, F., Diego-Más, J. A., Naranjo, V., ve Alcañíz, M. (2019). Automatic classification of human facial features based on their appearance. Plos One, 14(1), e0211314. https://doi.org/10.1371/journal.pone.0211314
14. Gençer, Y. G. (2017). Structural design of an e-commerce business: yemeksepeti.com example from Turkey. Chinese Business Review, 16(7). https://doi.org/10.17265/1537-1506/2017.07.003
15. Gian, M. ve Ikate, S. (2021). Development of electronic business from the historical point of view of an e-commerce concept. Journal Dimensie Management and Public Sector, 2(2), 19-24. https://doi.org/10.48173/jdmps.v2i2.91
16. Gökmen, A. (2011). Virtual business operations, e-commerce; its significance and the case of Turkey: current situation and its potential. Electronic Commerce Research, 12(1), 31-51. https://doi.org/10.1007/s10660-011-9084-2
17. Gui, X., Wu, X., ve Liu, S. (2014). Insight into the construction of occupational classification in e-commerce in China. IFIP Advances in Information and Communication Technology, 315-326. https://doi.org/10.1007/978-3-662-45526-5_29
18. Guo, L. ve Zhang, D. (2019). Ec-structure: establishing consumption structure through mining e-commerce data to discover consumption upgrade. Complexity, 2019, 1-8. https://doi.org/10.1155/2019/6543590
19. Gusarova, S., Gusarov, I., ve Smeretchinskiy, M. (2021). E-commerce trends and opportunities in brics countries. SHS Web of Conferences, 93, 04012. https://doi.org/10.1051/shsconf/20219304012
20. Gür, Y. E., Eşidir, K. A., & Şimşek, A. İ. (2024). Sağlık İstatistiklerinin Veri Madenciliği Teknikleri İle Analizi: Makine Öğrenmesi Algoritmaları Kullanılarak Genel Sağlık Durumunun Sınıflandırılması. Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, 24(6), 1364-1381. https://doi.org/10.35414/akufemubid.1491469
21. Hasanat, M. W., Hoque, A., ve Hamid, A. (2020). E-commerce optimization with the implementation of social media and seo techniques to boost sales in retail business. Journal of Marketing and Information Systems, 3(1), 1-5. https://doi.org/10.31580/jmis.v3i1.1193
22. Herzallah, D., Muñoz‐Leiva, F., ve Liébana‐Cabanillas, F. (2021). To buy or not to buy, that is the question: understanding the determinants of the urge to buy impulsively on instagram commerce. Journal of Research in Interactive Marketing, 16(4), 477-493. https://doi.org/10.1108/jrim-05-2021-0145
23. Hirano, M., Umeda, T., Okuda, T., Kawai, E., ve Yamaguchi, S. (2009). T-pim: trusted password input method against data stealing malware. 2009 Sixth International Conference on Information Technology: New Generations. https://doi.org/10.1109/itng.2009.35
24. Hong-qiang, Y. (2022). Research on e-commerce data standard system in the era of digital economy from the perspective of organizational psychology. Frontiers in Psychology, 13. https://doi.org/10.3389/fpsyg.2022.900698
25. Hossain, M. K., Salam, M. A., ve Jawad, S. S. (2022). Factors affecting online shopping behavior in bangladesh: a demographic perspective. International Journal of Business Ecosystem & Strategy (2687-2293), 4(3), 13-22. https://doi.org/10.36096/ijbes.v4i3.351
26. Hsieh, J. ve Liao, P. (2011). Antecedents and moderators of online shopping behavior in undergraduate students. Social Behavior and Personality: An International Journal, 39(9), 1271-1280. https://doi.org/10.2224/sbp.2011.39.9.1271
27. Hui, Y., Zheng, Z., ve Sun, C. (2022). E-commerce marketing optimization of agricultural products based on deep learning and data mining. Computational Intelligence and Neuroscience, 2022, 1-11. https://doi.org/10.1155/2022/6564014
28. Jensen, K. L., Yenerall, J., Chen, X., ve Yu, T. (2021). Us consumers’ online shopping behaviors and intentions during and after the covid-19 pandemic. Journal of Agricultural and Applied Economics, 53(3), 416-434. https://doi.org/10.1017/aae.2021.15
29. Kalhotra, S. K., Dongare, S. V., Kasthuri, A., ve Kaur, D. (2022). Data mining and machine learning techniques for credit card fraud detection. ECS Transactions, 107(1), 4977-4985. https://doi.org/10.1149/10701.4977ecst
30. Kaya, A. ve Aydın, Ö. (2019). E-commerce in turkey and sap integrated e-commerce system. International Journal of eBusiness and eGovernment Studies, 11(2), 207-225. https://doi.org/10.34111/ijebeg.20191128
31. Kaynak, E., Tatoğlu, E., ve Kula, V. (2005). An analysis of the factors affecting the adoption of electronic commerce by smes. International Marketing Review, 22(6), 623-640. https://doi.org/10.1108/02651330510630258
32. Khan, M. M., Sohrab, M. G., ve Yousuf, M. A. (2020). Customer gender prediction system on hierarchical e-commerce data. Beni-Suef University Journal of Basic and Applied Sciences, 9(1). https://doi.org/10.1186/s43088-020-0035-7
33. Kıran, S., Alan, B. ve Emre, İ. E. (2021). Investigation of the behaviors of users’ who shop from e-commerce sites. Acta Infologica, 5(2), 405-414. https://doi.org/10.26650/acin.887367
34. Li, J. (2022). E-commerce fraud detection model by computer artificial intelligence data mining. Computational Intelligence and Neuroscience, 2022, 1-9. https://doi.org/10.1155/2022/8783783
35. Luo, L., Liu, Y., ve Hu, T. (2016). Application and research of electronic commerce in the centralized procurement of large state-owned enterprises. DEStech Transactions on Economics and Management, (iceme-ebm). https://doi.org/10.12783/dtem/iceme-ebm2016/4156
36. Luo, Y., Yang, Z., Liang, Y., Zhang, X., ve Xiao, H. (2021). Exploring energy-saving refrigerators through online e-commerce reviews: an augmented mining model based on machine learning methods. Kybernetes, 51(9), 2768-2794. https://doi.org/10.1108/k-11-2020-0788
37. Mzwri, A. M. N. ve Altınkaya, Z. (2019). The impact of e-commerce on international trade: case of Turkey. International Journal of Contemporary Research and Review, 10(01), 21190-21209. https://doi.org/10.15520/ijcrr.v10i01.641
38. Ndagijimana, S., Ntaganda, J., Masabo, E., ve Kabano, I. (2023). Prediction of stunting among under-5 children in rwanda using machine learning techniques. Journal of Preventive Medicine and Public Health, 56(1), 41-49. https://doi.org/10.3961/jpmph.22.388
39. Oğuz, S., Dinçer, F. C. Y. ve Yirmibeşoğlu, G. (2022). E-commerce in eu countries and Turkey: an econometric analysis. Studies in Business and Economics, 17(3), 152-161. https://doi.org/10.2478/sbe-2022-0052
40. Öztürk, S. P. (2021). The era of digital transformation: visualizing the geography of e-commerce usage in Turkey. Environment and Planning A: Economy and Space, 53(6), 1241-1243. https://doi.org/10.1177/0308518x211007798
41. Pendyala, N. S., Rajasekaran, R., Manimekalai, R. ve Duraisamy, M. R. (2022). Awareness level of members of farmer producer organizations (fpos) about e-commerce platforms in agriculture. Asian Journal of Agricultural Extension, Economics & Sociology, 460-465. https://doi.org/10.9734/ajaees/2022/v40i931028
42. Phamthi, V. ve Ngominh, T. (2022). Disruptive innovation & chance for latecomer firms in e-commerce: the cases of the yes and pinduoduo. ENTRENOVA - Enterprise Research Innovation, 8(1), 364-376. https://doi.org/10.54820/entrenova-2022-0031
43. Priansa, D. J. ve Suryawardani, B. (2020). Effects of e-marketing and social media marketing on e-commerce shopping decisions. Jurnal Manajemen Indonesia, 20(1). https://doi.org/10.25124/jmi.v20i1.2800
44. Priyadarshini, P. ve Veeramanju, K. (2022). Business intelligence for the evaluation of customer satisfaction in e-commerce websites- a case study. International Journal of Management Technology and Social Sciences, 660-668. https://doi.org/10.47992/ijmts.2581.6012.0243
45. Salamai, A. A., Ageeli, A. A., ve El-kenawy, E. M. (2022). Forecasting e-commerce adoption based on bidirectional recurrent neural networks. Computers, Materials & Continua, 70(3), 5091-5106. https://doi.org/10.32604/cmc.2022.021268
46. Santos, J. (2003). E‐service quality: a model of virtual service quality dimensions. Managing Service Quality, 13(3), 233-246. https://doi.org/10.1108/09604520310476490
47. Selim, S., ve Balyaner, İ. (2017). Türkiye’de Hanehalkının Sahip Olduğu Bilişim Teknolojileri Ürünleri Sayısını Belirleyen Faktörlerin Araştırılması: Bir Sayma Veri Modeli. Mehmet Akif Ersoy Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 9(22), 428-454.
48. Sharma, A. (2021). Guided parallelized stochastic gradient descent for delay compensation. Applied Soft Computing, 102, 107084. https://doi.org/10.1016/j.asoc.2021.107084
49. Sheikh, S. M. ve Bastı, M. (2015). Customer satisfaction in business to consumer (b2c) e-commerce: a comparative study of Turkey and Pakistan. Eurasian Journal of Business and Economics, 8(16), 73-100. https://doi.org/10.17015/ejbe.2015.016.05
50. Singh, M. K., Rishi, O. P., Singh, A. K., Singh, P., ve Choudhary, P. (2021). Implementation of knowledge based collaborative filtering and machine learning for e-commerce recommendation system. Journal of Physics: Conference Series, 2007(1), 012032. https://doi.org/10.1088/1742-6596/2007/1/012032
51. Sugeng, F. A. (2021). Legal protection of e-commerce consumers through privacy data security. Advances in Social Science, Education and Humanities Research, https://doi.org/10.2991/assehr.k.210506.038
52. Tax, N., Vries, K. J. d., Jong, M. d., Dosoula, N., den, A. B. v., Smith, J., … ve Bernardi, L. (2021). Machine learning for fraud detection in e-commerce: a research agenda.. https://doi.org/10.48550/arxiv.2107.01979
53. Tharwat, A. (2020). Classification assessment methods. Applied Computing and Informatics, 17(1), 168-192. https://doi.org/10.1016/j.aci.2018.08.003
54. Toğaçar, M., Ergen, B., Cömert, Z., ve Özyurt, F. (2020). A deep feature learning model for pneumonia detection applying a combination of mRMR feature selection and machine learning models. Irbm, 41(4), 212-222. https://doi.org/10.1016/j.irbm.2019.10.006
55. TÜİK, (2023). Hanehalkı Bilişim Teknolojileri Kullanım Araştırması Mikro Veri Seti. Bilim ve Teknoloji İstatistikleri Grup Başkanlığı, Yayın No: 4708, Yayım Tarihi: Ekim 2023, ISBN: 978-625-8368-47-5.
56. Wang, C. ve Zhang, P. (2012). The evolution of social commerce: the people, management, technology, and information dimensions. Communications of the Association for Information Systems, 31. https://doi.org/10.17705/1cais.03105
57. Williams, P. W. ve Hubbard, P. (2001). Who is disadvantaged? retail change and social exclusion. The International Review of Retail, Distribution and Consumer Research, 11(3), 267-286. https://doi.org/10.1080/713770599
58. Wu, L., Cai, Y. ve Liu, D. (2011). Online shopping among chinese consumers: an exploratory investigation of demographics and value orientation. International Journal of Consumer Studies, 35(4), 458-469. https://doi.org/10.1111/j.1470-6431.2010.00982.x
59. Xiao, J. J. (2015). Internet and consumer economic wellbeing. Consumer Economic Wellbeing, 109-125. https://doi.org/10.1007/978-1-4939-2821-7_7
60. Yang, Z., Chen, C., Li, H., Yao, L. ve Zhao, X. (2020). Unsupervised classifications of depression levels based on machine learning algorithms perform well as compared to traditional norm-based classifications. Frontiers in Psychiatry, 11. https://doi.org/10.3389/fpsyt.2020.00045
61. Yin, H. (2021). Research on the relationship between consumption and demand of e-commerce in China. Learning & Education, 10(2), 122. https://doi.org/10.18282/l-e.v10i2.2300
62. Zamir, A., Khan, H. U., Iqbal, T., Yousaf, N., Aslam, F., Anjum, A., … ve Hamdani, M. (2020). Phishing web site detection using diverse machine learning algorithms. The Electronic Library, 38(1), 65-80. https://doi.org/10.1108/el-05-2019-0118
63. Zatonatska, T., Dluhopolskyi, O., Chyrak, I., ve Kotys, N. (2019). The internet and e-commerce diffusion in european countries (modeling at the example of austria, poland and ukraine). Innovative Marketing, 15(1), 66-75. https://doi.org/10.21511/im.15(1).2019.06
64. Zeng, Z., Rao, H., ve Liu, A. (2018). Research on personalized referral service and big data mining for e-commerce with machine learning. 2018 4th International Conference on Computer and Technology Applications (ICCTA). https://doi.org/10.1109/cata.2018.8398652
65. Zhang, M., Lu, J., Ma, N., Cheng, T., ve Hua, G. (2022). A feature engineering and ensemble learning based approach for repeated buyers prediction. Internatıonal Journal Of Computers Communications & Control, 17(6). https://doi.org/10.15837/ijccc.2022.6.4988
66. Zhang, Q., Abdullah, A. R., Chong, C. W. ve Ali, M. H. (2022). E-commerce information system management based on data mining and neural network algorithms. Computational Intelligence and Neuroscience, 2022, 1-11. https://doi.org/10.1155/2022/1499801