Estimation the Number of Visitor of E-Commerce Website by Artificial Neural Networks During Covid19 in Turkey

Developments in the field of internet technology affect human life in every way and cause their daily lives to positively change over time. One of the conveniences and positive effects provided by the internet has been e-commerce technology that has brought a new perspective to commerce and shopping for both the operator and client. Thanks to e-commerce, people can shop online by using websites and mobile applications, without needing to pay attention to the concepts such as easiness, speed, time and location. Due to these advantages, the interest in the e-commerce market is increasing daily in Turkey as it does in the rest of the world, the e-commerce market is also growing rapidly in line with the increasing demand. Through the process of COVID-19, public health is threatened, but also the economy and social life are affected. The process of quarantine and panic environment, which are the effects of a pandemic, affected shopping preferences of the public. The changes in the number of visitors of 4 e-commerce sites operating in Turkey during the COVID19 period were estimated in this study by artificial neural networks method. The number of visitors of websites were tried to be estimated by using statistical data such as new case, total case, new death, total death, new recovery, total recovery, intubation, intensive care, total test from March 11, which is when COVID-19 was first seen in Turkey, until May 13. The effects of the data that came about during the pandemic process on internet shopping were investigated in the study. The average R2 value of the system designed as a result of the test was 90%. Average MSE and MAE values were measured as 0.001 and 0.014, respectively. The fact that these values are close to zero shows that the success of the system is so high. Looking at the results, it can be said that the statistical data during the pandemic process have directly affect online shopping.

Covıd-19 Sürecinde Türkiye’deki E-Ticaret Sitelerinin Ziyaretçi Sayılarının Yapay Sinir Ağları ile Tahmini

İnternet teknolojisindeki gelişmeler insan hayatını her alanda etkilemekte ve zaman içerisinde günlük yaşantılarının olumlu yönde değişmesini sağlamaktadırlar. İnternetin sağlamış olduğu kolaylıklardan ve olumlu etkilerinden bir tanesi de işletmeci ve tüketici için ticarete ve alışverişe yeni bir bakış açısı getiren eticaret teknolojisi olmuştur. E-ticaret, internet üzerinden web sitelerini ve mobil uygularını kullanarak kolay, hızlı, zaman ve yer kavramından bağımsız olarak insanların alışveriş yapmasını sağlamaktadır. Bu avantajlarından dolayı tüm dünyada olduğu gibi Türkiye’de e-ticaret pazarına olan ilgi her geçen gün artmakta; artan taleple doğru orantılı olarak e-ticaret pazarı da hızla büyümektedir. COVID-19 süreci insanların sağlıklarını tehdit etmekle birlikte ekonomik ve sosyal yaşantılarını da etkilemektedir. Pandeminin etkileri olan karantina süreci ve panik ortamı insanların alışveriş tercihlerini etkilemiştir. Bu çalışmada Türkiye’de faaliyet gösteren 4 e-ticaret sitesinin COVID-19 süresince ziyaretçi sayılarındaki değişimler yapay sinir ağları yöntemiyle tahmin edilmiştir. Türkiye’de COVID-19’un ilk görüldüğü tarih olan 11 Mart tarihinden itibaren 13 Mayıs tarihine kadar olan yeni vaka, toplam vaka, yeni ölüm, toplam ölüm, yeni iyileşen, toplam iyileşen, entübe, yoğun bakım, toplam test gibi istatistiksel verileri kullanılarak, sitelerin ziyaretçi sayıları tahmin edilmeye çalışılmıştır. Çalışma sayesinde pandemi sürecinde oluşan verilerin, internet alışverişine etkileri araştırılmıştır. Test sonucunda tasarlanan sistemin ortalama R2 değeri% 90’dır. Ortalama MSE, MAE değerleri sırasıyla 0.001 ve 0.014 olarak ölçülmüştür. Bu değerlein sıfıra yakın olması, systemin başarısının da o kadar yüksek olduğunu göstermektedir. Elde edilen sonuçlara bakıldığında pandemi sürecindeki istatistiki verilerin internet alışverişini doğrudan etkilediği söylenebilir.

PDF

___

Arndt, C., & Lewis, J. D. (2001). The HIV/AIDS pandemic in South Africa: Sectoral impacts and unemployment. Journal of International Development: The Journal of the Development Studies Association, 13(4), 427-449. https://onlinelibrary.wiley.com/doi/abs/10.1002/jid.796

Anggrainingsih, R., Aprianto, G. R., & Sihwi, S. W. (2015, October). Time series forecasting using exponential smoothing to predict the number of website visitor of Sebelas Maret University. In 2015 2nd International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE) (pp. 14-19). IEEE.

Bermejo, A. (2004). HIV/AIDS in Africa. New Economy, 11(3), 164-169. https://onlinelibrary.wiley.com/doi/abs/10.1111/j.1468-0041.2004.00357.x

Chai, T., & Draxler, R. R. (2014). Root mean square error (RMSE) or mean absolute error (MAE)?– Arguments against avoiding RMSE in the literature. Geoscientific model development, 7(3), 1247-1250.

Chun, S.-H., Kim, J.-C. (2005). Pricing strategies in B2C electronic commerce: analytical and empirical approaches. Decision Support Systems, 40(2), 375-388. https://doi.org/10.1016/j.dss.2004.04.012

Coppel, J. (2000). E-commerce: impacts and policy challenges. 1-26. https://doi.org/10.1787/801315684632

Defibaugh-Chavez, P., Mukkamala, S., & Sung, A. H. (2004, December). Web site visitor classiflcation using machine learning. In Fourth International Conference on Hybrid Intelligent Systems (HIS'04) (pp. 384-389). IEEE.

Gershenson, C. (2003). Artificial neural networks for beginners.

Gülkesen, K. H., İşleyen, F., Saka, O. (2001). Türkiye'de Sağlık Alanında Sivil Toplum Örgütleri Web'i Nasıl Kullanıyor? 7. Türkiye'de İnternet Konferansı. Istanbul. Türkey.

Gupta, H. V., Kling, H., Yilmaz, K. K., & Martinez, G. F. (2009). Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling. Journal of hydrology, 377(1-2), 80-91.

Hanashima, M., Tomobe, K.I. (2012). Urbanization, industrialization, and mortality in modern Japan: a spatio-temporal perspective. Annals of GIS, 18(1), 57-70. https://doi.org/10.1080/19475683.2011.647078

Hartono, E., Holsapple, C. W., Kim, K.-Y., Na, K.-S., Simpson, J. T. (2014). Measuring perceived security in B2C electronic commerce website usage: A respecification and validation. Decision Support Systems, 62, 11-21. https://doi.org/10.1016/j.dss.2014.02.006

Hasanat, M. W., Hoque, A., Shikha, F. A., Anwar, M., Hamid, A. B. A., Tat, H. H. (2020). The Impact of Coronavirus (Covid-19) on E-Business in Malaysia. Asian Journal of Multidisciplinary Studies, 3(1), 85-90.

Johnson, H. C., Gossner, C. M., Colzani, E., Kinsman, J., Alexakis, L., Beauté, J., Würz, A., Tsolova, S., Bundle, N., Ekdahl, K. (2020). Potential scenarios for the progression of a COVID-19 epidemic in the European Union and the European Economic Area, Eurosurveillance, 25(9), 2000202.

Jones, K., Leonard, L. N. (2014). Factors Influencing Buyer's Trust in Consumer-to-Consumer E Commmerce. Journal of Computer Information Systems, 54(4), 71-79. https://doi.org/10.1080/08874417.2014.11645724

Kırık, A. M. (2017). E-Commerce Applications On Facebook In Turkey: Tesbihane And Çaykur. 2, 525-542. https://doi.org/10.9761/JASSS3547_

Lucking-Reiley, D., Spulber, D. F. (2001). Business-to-business electronic commerce. Journal of Economic Perspectives, 15(1), 55-68. https://doi.org/10.1257/jep.15.1.55

Ministry of Health, R.T. (2020). New Coronary Virus Disease (COVID-19). https://covid19bilgi.saglik.gov.tr/tr/

Movahedi-Lankarani, S. J. (2003). Best of the Web: E-Commerce. Journal of Business & Finance Librarianship, 8(3-4), 133-151. https://doi.org/10.1300/J109v08n03_02

Nagelkerke, N. J. (1991). A note on a general definition of the coefficient of determination. Biometrika, 78(3), 691-692.

Öztemel, E. (2003). Yapay sinir ağlari. PapatyaYayincilik

Ranganathan, C., Ganapathy, S. (2002). Key dimensions of business-to-consumer web sites. Information & Management, 39(6), 457-465. https://doi.org/10.1016/S0378- 7206(01)00112-4

Sağıroğlu, Ş., Beşdok, E., Erler, M. (2003). Artificial Intelligence Applications in Engineering, Artificial Neural Networks I. Ufuk Publising.

Siche, R. (2020). What is the impact of COVID-19 disease on agriculture? Scientia Agropecuaria, 11(1), 3-6. http://dx.doi.org/10.17268/sci.agropecu.2020.01.00

Tkáč, M., & Verner, R. (2016). Artificial neural networks in business: Two decades of research. Applied Soft Computing, 38, 788-804. https://doi.org/10.1016/j.asoc.2015.09.040

websiteiq. (2020). Website Traffic Statistics. https://www.websiteiq.com/

Weltevreden, J. W., & Rotem-Mindali, O. (2009). Mobility effects of b2c and c2c e-commerce in the Netherlands: a quantitative assessment. Journal of Transport Geography, 17(2), 83-92. https://doi.org/10.1016/j.jtrangeo.2008.11.005

Wikipedia. (2020a). GittiGidiyor.com. tr.wikipedia.org/w/index.php?title=GittiGidiyor&oldid=21745391

Wikipedia. (2020b). Hepsiburada.com.tr. wikipedia.org/w/index.php?title=Hepsiburada&oldid=22432016

Wikipedia. (2020c). N11.com. tr.wikipedia.org/w/index.php? title=N11.com&oldid=22028910

Wikipedia. (2020d). Sahibinden.com. tr.wikipedia.org/w/index.php?title=Sahibinden.com&oldid=22317651

Wu, F., Li, H.-H., & Kuo, Y.-H. (2011). Reputation evaluation for choosing a trustworthy counterparty in C2C e-commerce. Electronic Commerce Research and Applications, 10(4), 428-436. https://doi.org/10.1016/j.elerap.2010.09.004

Yaman, Y. (2018). Müşterilerin Mobil Alışveriş Kanalını Kullanma Niyetini Etkileyen Faktörler.

Tüketici ve Tüketim Araştırmaları Dergisi= Journal of Consumer and Consumption Research, 10(1), 1-27.

Yang, J., & Papazoglou, M. P. (2000). Interoperation support for electronic business. Communications of the ACM, 43(6), 39-47.

Zeng, Y. E., Wen, H. J., Yen, D. C. (2003). Customer relationship management (CRM) in business‐ to‐business (B2B) e‐commerce. Information Management & Computer Security. https://doi.org/10.1108/09685220310463722