ESTIMATION OF AUTOMOBILE SALES WITH ARTIFICIAL NEURAL NETWORK USING DATA OF ONLINE CONSUMER ENGAGEMENT AND SEARCH ENGINE

Öz

Estimation of sales volume affects many segments of the enterprises from raw material purchase to advertising expenses. A large number of consumer data is needed to be used in sales forecasting. The use of many consumer data is private, causing problems. On the other hand, data from social networks and search engines, which are influential in the purchasing decision process, are valuable and accessible to everyone. For businesses, it is important to estimate sales figures accurately. For consumers, protecting their personal data is substantial. In this study, it is aimed to estimate the sales volume of an automobile brand by using Online Consumer Engagement and search engine data which are effective in the purchasing decision process of consumers and publicly available. 2267 posts, created between 2012-2017, likes, comments, and sharing data of these posts were taken from Facebook brand page of the business where Online Consumer Engagement is intense using Facebook Graph API. Search engine data was obtained from Google Trends, and sales data was obtained from Automotive Distributors Association website. Data were normalized by Min-Max method and analyzed by feedforward artificial neural networks and Bayesian Regulation backpropagation method. Successful sales volume estimation, whose the correlation value is %74 and mean error value is %1, was made with Facebook brand page and search engine data. In addition, detailed data covering 6 years has been prepared and presented as descriptive information. In the study, successful sales estimation was made without using the private information of the consumers. This study contributes to the sector and academic literature by relying on real data and using artificial neural networks in the business administration.

Anahtar Kelimeler

• Online Consumer Engagement,Search Engine,Sales Estimation,Artificial Neural Networks,Bayesian Regulation

ÇEVRİMİÇİ TÜKETİCİ BÜTÜNLEŞMESİ VE ARAMA MOTORU VERİLERİ KULLANILARAK YAPAY SİNİR AĞLARI İLE OTOMOBİL SATIŞ TAHMİNİ

Öz

Satış miktarının tahmin edilmesi hammadde alımından reklam giderlerinin belirlenmesine kadar işletmelerde birçok bölüme etki etmektedir. Satış tahmininde kullanılmak üzere çok sayıda tüketici verisine ihtiyaç duyulmaktadır. Birçok tüketici verisinin kişisel olması nedeniyle kullanılması sorun oluşturmaktadır. Buna karşın, satın alma karar sürecinde etkili olan sosyal ağlar ve arama motorlarına ait veriler değerli olmanın yanında herkesin erişimine açıktır. İşletmeler için satış rakamlarının gerçeğe yakın tahmin edilmesi ve tüketiciler için ise kişisel verilerin korunması önemlidir. Bu bağlamda, çalışmada tüketicilerin satın alma karar sürecinde etkili ve halka açık olan Çevrimiçi Tüketici Bütünleşme ve arama motoru verileri kullanılarak bir otomobil markasının satış miktarının tahmin edilmesi amaçlanmıştır. Çevrimiçi Tüketici Bütünleşmesinin yoğun yaşandığı işletmeye ait Facebook marka sayfasından 2012-2017 yılları arasında oluşturulan 2267 adet gönderi ve bu gönderilere ait beğenme, yorum ve paylaşma verileri Facebook Graph API ile alınmıştır. Arama motoru verileri Google Trends, satış verileri Otomotiv Distribütörleri Derneği web sitesinden elde edilmiştir. Veriler Min-Max yöntemiyle normalleştirilmiş ve yapay sinir ağları, Bayesian Regülasyon geri yayılım yöntemiyle analiz edilmiştir. Facebook marka sayfası ve arama motoru verileriyle %74 korelasyon ve %1 ortalama hata değeriyle başarılı satış miktarı tahmini yapılmıştır. Ayrıca 6 yılı kapsayan detaylı veriler düzenlenerek tanımlayıcı bilgiler olarak sunulmuştur.  Çalışmada tüketicilerin özel bilgileri kullanılmadan başarılı satış tahminlemesi yapılmıştır. Bununla birlikte, çalışma gerçek verilere dayanması ve yapay sinir ağlarının işletme alanında kullanımıyla sektöre ve akademik yazına katkı sağlamaktadır.

Anahtar Kelimeler

• Çevrimiçi Tüketici Bütünleşmesi,Arama Motoru,Satış Tahmini,Yapay Sinir Ağları,Bayesian Regülasyon

Kaynakça

1. Ahn, H. il ve Spangler, W. S. (2014). Sales prediction with social media analysis. Annual SRII Global Conference, SRII, 213–222. doi:10.1109/SRII.2014.37
2. Aşkın, D., İskender, İ. ve Mamızadeh, A. (2011). Farklı Yapay Sinir Ağları Yöntemlerini Kullanarak Kuru Tip Transformatör Sargısının Termal Analizi, 26(4), 905–913.
3. Atsalakis, G. S., Atsalaki, I. G. ve Zopounidis, C. (2018). Forecasting the success of a new tourism service by a neuro-fuzzy technique. European Journal of Operational Research, 268(2), 716–727. doi:10.1016/j.ejor.2018.01.044
4. Barreira, N., Godinho, P. ve Melo, P. (2013). Nowcasting unemployment rate and new car sales in south-western Europe with Google Trends. NETNOMICS: Economic Research and Electronic Networking, 14(3), 129–165. doi:10.1007/s11066-013-9082-8
5. Berthon, P. R., Pitt, L. F., Plangger, K. ve Shapiro, D. (2012). Marketing Meets Web 2.0, Social Media, and Creative Consumers: Implications for International Marketing Strategy. Business Horizons, 55(3), 261–271. doi:10.1016/j.bushor.2012.01.007
6. Caner, E. (2012). Türkiye’de Facebook Kullanıcı Sayısı Hangi Durumlarda Artar?
7. Cerit, I., Yildirim, A., Ucar, M. K., Demirkol, A., Cosansu, S. ve Demirkol, O. (2017). Estimation of antioxidant activity of foods using artificial neural networks. Journal of Food and Nutrition Research, 56(2), 138–148.
8. Choi, H. ve Varian, H. (2012). Predicting the Present with Google Trends. Economic Record, 88(SUPPL.1), 2–9. doi:10.1111/j.1475-4932.2012.00809.x

9. Chopra, S., Yadav, D. ve Chopra, A. N. (2019). International Journal of Swarm Intelligence and Evolutionary Computation Artificial Neural Networks Based Indian Stock Market Price Prediction : Before and After Demonetization, 8(1), 1–7. doi:10.4172/2090-4908.1000174
10. Chu, S. C. ve Kim, Y. (2011). Determinants of Consumer Engagement in Electronic Word-Of-Mouth (eWOM) in Social Networking Sites. International Journal of Advertising, 30(1). doi:10.2501/IJA-30-1-047-075
11. Çuhadar, M. ve Kayacan, C. (2005). Yapay Sinir Ağları Kullanılarak Konaklama İşletmelerinde Doluluk Oranı Tahmini : Türkiye ’ deki Konaklama İşletmeleri Üzerine Bir Deneme, 24–30.
12. Cunha, M. da. (2019). 5 Reasons You Should Be Advertising on Facebook. wordstream.com. 8 Nisan 2019 tarihinde https://www.wordstream.com/blog/ws/2015/10/14/advertising-on-facebook adresinden erişildi.
13. Cvijikj, I. P. ve Michahelles, F. (2013). Online engagement factors on Facebook brand pages. Social Network Analysis and Mining, 3(4), 843–861. doi:10.1007/s13278-013-0098-8
14. De Vries, L., Gensler, S. ve Leeflang, P. S. H. (2012). Popularity of Brand Posts on Brand Fan Pages: An Investigation of the Effects of Social Media Marketing. Journal of Interactive Marketing, 26(2), 83–91. doi:10.1016/j.intmar.2012.01.003
15. Ding, X., Liu, T., Duan, J. ve Nie, J.-Y. (2015). Mining User Consumption Intention from Social Media Using Domain Adaptive Convolutional Neural Network. Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI’15), 2389–2395.
16. Doğru, F. (2015). Güncel Optimizasyon Yöntemleri Kullanılarak Rezidüel Gravite Anomalilerinden Parametre Kestirimi. Yerbilimleri/Hacettepe Üniversitesi Yerbilimleri Uygulama ve Araştırma Merkezi Dergisi, 36(1), 31–43. doi:10.17824/yrb.71895
17. Doorn, J. van, Lemon, K. N., Mittal, V., Nass, S., Pick, D., Pirner, P. ve Verhoef, P. C. (2010). Customer Engagement Behavior: Theoretical Foundations and Research Directions. Journal of Service Research, 13(3), 253–266. doi:10.1177/1094670510375599
18. Ellison, N. B. ve Boyd, D. (2007). Social Network Sites: Definition, History, and Scholarship. Journal of Computer-Mediated Communication, 210–230. doi:10.1111/j.1083-6101.2007.00393.x
19. Etter, M. ve Fieseler, C. (2010). On Relational Capital in Social Media. Studies in Communication Sciences, 10(2), 167–189.
20. Forrester Consulting. (2008). How Engaged are Your Customers ?, (September), 1–22. http://www.indigopacific.com/pdf/Forrester_TLP_How_Engaged_Are_Your_Customers.pdf adresinden erişildi.
21. Funk, T. (2010). Advanced social media marketing: How to lead, launch, and manage a successful social media program. Press.
22. Gordini, N., Sanpaolo, I. ve Veglio, V. (2015). Customer relationship management and data mining : A classification decision tree to predict customer purchasing behavior in global market. doi:10.4018/978-1-4666-4450-2.ch001
23. Gupta, R. ve Pathak, C. (2014). A Machine Learning Framework for Predicting Purchase by online customers based on Dynamic Pricing. Procedia - Procedia Computer Science, 36, 599–605. doi:10.1016/j.procs.2014.09.060
24. Hapsari, R., Clemes, M. D. ve Dean, D. (2017). The impact of service quality, customer engagement and selected marketing constructs on airline passenger loyalty. International Journal of Quality and Service Sciences, 9(1), 21–40. doi:10.1108/IJQSS-07-2016-0048
25. Hollebeek, L. (2011). Exploring customer brand engagement: definition and themes. Journal of Strategic Marketing, 19(7), 555–573. doi:10.1080/0965254X.2011.599493
26. Jayalakshmi, T. ve Santhakumaran, A. (2011). Statistical Normalization and Back Propagationfor Classification. International Journal of Computer Theory and Engineering, 3(1), 89–93. doi:10.7763/IJCTE.2011.V3.288
27. Ji, Y. G., Li, C., North, M. ve Liu, J. (2017). Staking Reputation on Stakeholders: How Does Stakeholders’ Facebook Engagement Help or Ruin a Company’s Reputation? Public Relations Review, 43(1), 201–210. doi:10.1016/j.pubrev.2016.12.004
28. Kelleher, T. (2009). Conversational voice, communicated commitment, and public relations outcomes in interactive online communication. Journal of Communication, 59(1), 172–188. doi:10.1111/j.1460-2466.2008.01410.x
29. Kim, H. W., Gupta, S. ve Koh, J. (2011). Investigating the intention to purchase digital items in social networking communities: A customer value perspective. Information and Management, 48(6), 228–234. doi:10.1016/j.im.2011.05.004
30. King, M. A., Abrahams, A. S. ve Ragsdale, C. T. (2014). Ensemble methods for advanced skier days prediction. Expert Systems with Applications, 41(4), 1176–1188. doi:10.1016/J.ESWA.2013.08.002
31. Kotler, P., Keller, K. L. (2012). Marketing Management 14E. New York: Pearson Education Inc.
32. Lassen, N. B., Madsen, R. ve Vatrapu, R. (2014). Predicting iPhone Sales from iPhone Tweets. Proceedings . IEEE 18th international Enterprise Distributed object computing conference, 2014–Decem(December), 81–90. doi:10.1109/EDOC.2014.20
33. MacKay, D. J. C. (1992). A Practical Bayesian Framework for Backpropagation Networks. EFSA Journal, 4, 448–472. doi:10.2903/j.efsa.2018.5430
34. McCulloch, A. (2015). Measuring the Right Social KPIs. SocialBakers. 2 Mart 2018 tarihinde https://www.socialbakers.com/blog/2384-measuring-the-right-social-kpis adresinden erişildi.
35. Mudambi, S. M. ve Schuff, D. (2010). What Makes a Helpful Online Review? A Study of Customer Reviews on Amazon.com. MIS Quarterly, 34(1), 185–200. doi:Article
36. ODD. (2017). 2017 Yılı (Ocak-Aralık) Perakende Satışlar (Yerli&İthal). Otomotiv Distribütörleri Derneği. 5 Ağustos 2019 tarihinde http://www.odd.org.tr/web_2837_1/sortial.aspx?linkpos=3&target=categorial1&type=36&primary_id=&detail=single&sp_table=&sp_primary=&sp_fields=&sp_language=&sp_table_extra=&extracriteria=&language_id=1&search_fields=&search_values= adresinden erişildi.
37. Park, S. ve Huh, S. (2019). A Social Network-Based Inference Model for Validating Customer Profile Data, 36(4), 1217–1237.
38. Qiu, J., Lin, Z. ve Li, Y. (2015). Predicting customer purchase behavior in the e-commerce context. Electronic Commerce Research, 15(4), 427–452. doi:10.1007/s10660-015-9191-6
39. Richter, D., Riemer, K. ve vom Brocke, J. (2011). Internet Social Networking. Wirtschaftsinformatik, 53(2), 89–103.
40. Rybalko, S. ve Seltzer, T. (2010). Dialogic Communication in 140 Characters or Less: How Fortune 500 Companies Engage Stakeholders Using Twitter. Public Relations Review, 36(4), 336–341. doi:10.1016/j.pubrev.2010.08.004
41. Sakar, C. O., Polat, S. O., Katircioglu, M. ve Kastro, Y. (2018). Real-time prediction of online shoppers ’ purchasing intention using multilayer perceptron and LSTM recurrent neural networks. Neural Computing and Applications, 0. doi:10.1007/s00521-018-3523-0
42. Schmidt, T. ve Vosen, S. (2009). Forecasting Private Consumption. Economic Papers, 155, 23.
43. Search Engine Market Share Worldwide. (2019).statcounter.com. 28 Temmuz 2019 tarihinde http://gs.statcounter.com/search-engine-market-share adresinden erişildi.
44. Si, S. (2016). Social Media and Its Role in Marketing. Business and Economics Journal, 07(01), 1–5. doi:10.4172/2151-6219.1000203
45. Sola, J. ve Sevilla, J. (1997). Importance of Input Data Normalization for the Application of Neural Networks to Complex Industrial Problems, 44(3), 1464–1468.
46. Stelzner, M. A. (2014). 2014 Social Media Marketing Industry Report. How Marketers Are Using Social Media to Grow Their Businesses, (May), 1–52. papers3://publication/uuid/C53C1FA9-9CA1-430B-8E0E-89CAE65678A2 adresinden erişildi.
47. Sullivan, D. (2016). Google now handles at least 2 trillion searches per year. Search Engine Land. 28 Temmuz 2019 tarihinde https://searchengineland.com/google-now-handles-2-999-trillion-searches-per-year-250247 adresinden erişildi.
48. Vellido, A. (1999). Neural networks in business: a survey of applications (1992–1998). Expert Systems with Applications, 17(1), 51–70. doi:10.1016/S0957-4174(99)00016-0
49. Vellido, A., Lisboa, P. J. G. ve Meehan, K. (2015). Quantitative Characterization and Prediction of On-Line Purchasing Behavior : A Latent Variable Approach Approach, 4415. doi:10.1080/10864415.2000.11518380
50. Wang, X., Yu, C. ve Wei, Y. (2012). Social Media Peer Communication and Impacts on Purchase Intentions: A Consumer Socialization Framework. Journal of Interactive Marketing, 26(4), 198–208. doi:10.1016/j.intmar.2011.11.004
51. We Are Social. (2018). Digital in 2018: World’s internet users pass the 4 billion mark. Janurary, (January), 153. https://wearesocial.com/uk/blog/2018/01/global-digital-report-2018 adresinden erişildi.
52. Wu, L. ve Brynjolfsson, E. (2015). Volume Title : Economic Analysis of the Digital Economy Publication Date : April 2015 Chapter Title : The Future of Prediction : How Google Searches Foreshadow Housing Prices and Sales The Future of Prediction How Google Searches Foreshadow Housing Prices. doi:10.3386/w19549
53. Yadav, M. S., de Valck, K., Hennig-Thurau, T., Hoffman, D. L. ve Spann, M. (2013). Social commerce: A contingency framework for assessing marketing potential. Journal of Interactive Marketing, 27(4), 311–323. doi:10.1016/j.intmar.2013.09.001
54. Yang, S. U., Kang, M. ve Johnson, P. (2010). Effects of Narratives, Openness to Dialogic Communication, and Credibility on Engagement in Crisis Communication Through Organizational Blogs. Communication Research, 37(4), 473–497. doi:10.1177/0093650210362682
55. Yu, L., Wang, S. ve Lai, K. K. (2007). Foreign-Exchange-Rate Forecasting with Artificial Neural Networks. Springer Science & Business Media.
56. Zhang, Z. (2018). Multivariate Time Series Analysis in Climate and Environmental Research. doi:10.1007/978-3-319-67340-0