LSTM YÖNTEMİ İLE EKONOMİK GÖSTERGELER KULLANILARAK OTOMOBİL SATIŞ TAHMİNİ

Year 2022, , 1481 - 1492, 02.10.2022

Mustafa Yurtsever

https://doi.org/10.30783/nevsosbilen.987093

Abstract

Otomativ sanayi birçok ülke için en önemli sanayi kollarından birisidir. Bu nedenle araç satışlarına ilişkin tahminler otomotiv sanayisine ve tedarikçilerine değerli bilgiler sağlamaktadır. Otomobil satışları, piyasa ortamı, ekonomik kriz, petrol fiyatlarındaki artış, vergi avantajları, faiz oranları gibi dış faktörlerden etkilenmektedir. Otomobil endüstrisinin uzun vadeli tahminlerle ilgilendiği göz önüne alındığında, basit tek değişkenli modeller yeterli değildir. Çok değişkenli modeller araç satışlarını tahmin etmede daha iyi sonuçlar verebilmektedir. Derin öğrenmenin güçlü temsil yeteneği ve satış tahmini uygulamalarında kullanılması hem işletmeler hem de araştırmacılar tarafından büyük ilgi görmektedir. LSTM modelinin zaman serilerindeki başarısı göz önüne alınarak bu çalışmada çok değişkenli zaman serileri kullanılarak araç satış tahmini yapılmıştır. Çalışmada modelin girdileri olarak petrol fiyatı, işsizlik oranı, tüketici fiyat endeksi gibi ekonomik göstergeler kullanılmıştır. Sonuçlar LSTM’nin çok değişkenli zaman serilerinde tahmin doğruluğu açısından iyi performans sergilediğini göstermektedir.

Keywords

Ekonomik Göstergeler, LSTM, Otomobil Satış Tahmin, Zaman Serileri

References

• Abbasimehr, H., Shabani, M., & Yousefi, M. (2020). An optimized model using LSTM network for demand forecasting. Computers & industrial engineering, 143.
• Arslankaya, S., & Öz, V. (2018). Time series analysis of sales quantity in an automotive company and estimation by Artificial Neural Networks. Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 22(5), 1482-1492.
• Du, S., Li, T., Yang, Y., & Horng, S. J. (2020). Multivariate time series forecasting via attention-based encoder–decoder framework. Neurocomputing, 388, 269-279.
• Fantazzini, D., & Toktamysova, Z. (2015). Forecasting German car sales using Google data and multivariate models. International Journal of Production Economics, 170, 97-135.
• Federal Reserve Bank of St. Louis. (2021, Feb. 4). 10-Year Breakeven Inflation Rate [T10YIEM], Federal Reserve Bank of St. Louis, 2021. [Online]. Available: https://fred.stlouisfed.org/series/T10YIEM
• Gao, J., Xie, Y., Cui, X., Yu, H., & Gu, F. (2018). Chinese automobile sales forecasting using economic indicators and typical domestic brand automobile sales data: A method based on econometric model. Advances in Mechanical Engineering, 10(2), 1-11.
• Hatcher, W. G., & Yu, W. (2018). A survey of deep learning: Platforms, applications and emerging research trends. IEEE Access, 6, 24411-24432.
• Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.
• Karaatlı, M., Helvacıoğlu, Ö. C., Ömürbek, N., & Tokgöz, G. (2012). Yapay Sinir Ağlari Yöntemi ile Otomobil Satiş Tahmini. Uluslararası Yönetim İktisat ve İşletme Dergisi, 8(17), 87-100.
• Karim, F., Majumdar, S., Darabi, H., & Harford, S. (2019). Multivariate LSTM-FCNs for time series classification. Neural Networks, 116, 237-245.
• Kaya, A., Kaya, G., & Çebi, F. (2019). Forecasting automobile sales in Turkey with artificial neural networks. International Journal of Business Analytics (IJBAN), 6(4), 50-60.
• Kayapınar Kaya, S. K., & Yıldırım, Ö. (2020). A Predıctıon Model For Automobıle Sales In Turkey Usıng Deep Neural Networks. Endüstri Mühendisliği, 31(1), 57-74.
• Kuvvetli, Y., Dağsuyu, C., & Oturakci, M. (2015). Türkiye'deki Araç Satışları İçin Ekonomik ve Çevresel Faktörleri Göz Önüne Alan Yapay Sinir Ağı Tabanlı Bir Tahmin Yaklaşımı. Endüstri Mühendisliği, 26(3), 23-31.
• LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444.
• Lee, W. I., Shih, B. Y., & Chen, C. Y. (2012). Retracted: A hybrid artificial intelligence sales‐forecasting system in the convenience store industry. Human Factors and Ergonomics in Manufacturing & Service Industries, 22(3), 188-196.
• Munkhdalai, L., Munkhdalai, T., Park, K. H., Amarbayasgalan, T., Batbaatar, E., Park, H. W., & Ryu, K. H. (2019). An end-to-end adaptive input selection with dynamic weights for forecasting multivariate time series. IEEE Access, 7, 99099-99114.
• Nguyen, H. D., Tran, K. P., Thomassey, S., & Hamad, M. (2021). Forecasting and Anomaly Detection approaches using LSTM and LSTM Autoencoder techniques with the applications in supply chain management. International Journal of Information Management, 57, 1-13.
• Nunnari, G., & Nunnari, V. (2017). Forecasting monthly sales retail time series: a case study. In 2017 IEEE 19th conference on business informatics (CBI), 1, 1-6.
• Olah, C. (2015). Understanding lstm networks. https://colah.github.io/posts/2015-08-Understanding-LSTMs.
• Organization for Economic Co-operation and Development. (2021, Feb. 4). Consumer Price Index: Total All Items for the United States [CPALTT01USM657N], Federal Reserve Bank of St. Louis, 2021. [Online]. Available: https://fred.stlouisfed.org/series/CPALTT01USM657N
• Pai, P. F., & Liu, C. H. (2018). Predicting vehicle sales by sentiment analysis of Twitter data and stock market values. IEEE Access, 6, 57655-57662.
• Parmezan, A. R. S., Souza, V. M., & Batista, G. E. (2019). Evaluation of statistical and machine learning models for time series prediction: Identifying the state-of-the-art and the best conditions for the use of each model. Information sciences, 484, 302-337.
• Ramos, P., Santos, N., & Rebelo, R. (2015). Performance of state space and ARIMA models for consumer retail sales forecasting. Robotics and computer-integrated manufacturing, 34, 151-163.
• Sa-ngasoongsong, A., Bukkapatnam, S. T., Kim, J., Iyer, P. S., & Suresh, R. P. (2012). Multi-step sales forecasting in automotive industry based on structural relationship identification. International Journal of Production Economics, 140(2), 875-887.
• Sánchez, A. M., & Pérez, M. P. (2005). Supply chain flexibility and firm performance: a conceptual model and empirical study in the automotive industry. International Journal of Operations & Production Management, 25(7), 681-700.
• Shahabuddin, S. (2009), "Forecasting automobile sales", Management Research News, 32(7), 670-682.
• Shen, Z., Zhang, Y., Lu, J., Xu, J., & Xiao, G. (2020). A novel time series forecasting model with deep learning. Neurocomputing, 396, 302-313.
• Song, X., Liu, Y., Xue, L., Wang, J., Zhang, J., Wang, J., ... & Cheng, Z. (2020). Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model. Journal of Petroleum Science and Engineering, 186.
• Topal, İ. Çevrimiçi Tüketici Bütünleşmesi Ve Arama Motoru Verileri Kullanılarak Yapay Sinir Ağları İle Otomobil Satış Tahmini. Nevşehir Hacı Bektaş Veli Üniversitesi SBE Dergisi, 9(2), 534-551.
• U.S. Bureau of Economic Analysis. (2021, Feb. 4). Total Vehicle Sales [TOTALNSA], Federal Reserve Bank of St. Louis, 2021. [Online]. Available: https://fred.stlouisfed.org/series/TOTALNSA.
• U.S. Bureau of Economic Analysis. (2021, Feb. 4). Personal Consumption Expenditures Excluding Food and Energy (Chain-Type Price Index) [PCEPILFE], Federal Reserve Bank of St. Louis, 2021. [Online]. Available: https://fred.stlouisfed.org/series/PCEPILFE.
• U.S. Energy Information Administration. (2021, Feb. 4). Crude Oil Prices: West Texas Intermediate (WTI) - Cushing, Oklahoma [DCOILWTICO], Federal Reserve Bank of St. Louis, 2021. [Online]. Available: https://fred.stlouisfed.org/series/DCOILWTICO.
• U.S. Bureau of Labor Statistics. (2021, Feb. 4). Unemployment Rate [UNRATENSA], Federal Reserve Bank of St. Louis, 2021. [Online]. Available: https://fred.stlouisfed.org/series/UNRATENSA.
• U.S. Bureau of Labor Statistics. (2021, Feb. 2). Producer Price Index by Commodity: All Commodities [PPIACO], Federal Reserve Bank of St. Louis, 2021. [Online]. Available: https://fred.stlouisfed.org/series/PPIACO.
• Xia, Z., Xue, S., Wu, L., Sun, J., Chen, Y., & Zhang, R. (2020). ForeXGBoost: passenger car sales prediction based on XGBoost. Distributed and Parallel Databases, 38, 713-738.
• Wachter, P., Widmer, T., & Klein, A. (2019). Predicting automotive sales using pre-purchase online search data. In 2019 Federated Conference on Computer Science and Information Systems (FedCSIS), 18, 569-577.
• Wang, F. K., Chang, K. K., & Tzeng, C. W. (2011). Using adaptive network-based fuzzy inference system to forecast automobile sales. Expert Systems with Applications, 38(8), 10587-10593.
• Yan, H. S., & Tu, X. (2012). Short-term sales forecasting with change-point evaluation and pattern matching algorithms. Expert systems with applications, 39(5), 5426-5439.
• Yang, B., Sun, S., Li, J., Lin, X., & Tian, Y. (2019). Traffic flow prediction using LSTM with feature enhancement. Neurocomputing, 332, 320-327.
• Yang, Z., & Zhang, C. (2020, July). Automobile Sales Forecast Based on Web Search and Social Network Data. The 11th International Conference on E-business, Management and Economics, 37-41.
• Zhang, G. P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, 159-175.
• Zhang, Y., Zhong, M., Geng, N., & Jiang, Y. (2017). Forecasting electric vehicles sales with univariate and multivariate time series models: The case of China. PloS one, 12(5), 1-15.