SATIŞ TAHMİNİ İÇİN DERİN ÖĞRENME YÖNTEMLERİNİN KARŞILAŞTIRILMASI

Öz

Dijital dönüşüm ile tedarik zinciri yönetiminde büyük veri analitiğinin önemi gün geçtikçe artmaktadır. Özellikle müşteri taleplerinin hızlı ve doğru tahmin edilmesinde büyük verinin kullanımı firmalara rekabet avantajı sağlamaktadır. Bu doğrultuda, yapay zekâ tekniklerinden biri olan derin öğrenme modelleri büyük verideki karmaşık örüntülerin keşfedilmesinde öne çıkmaktadır. Son yıllarda literatürde çok sayıda derin öğrenme yöntemi önerilmiştir. Bu çalışmada, satış tahmini problemi için derin öğrenme yöntemlerinin performansları karşılaştırılmıştır. Bu kapsamda derin sinir ağı (DNN), derin otokodlayıcı (Deep AE), evrişimli sinir ağı (CNN), tekrarlayan sinir ağı (RNN), uzun kısa-süreli bellek (LSTM) ağı, çift yönlü LSTM (Bi-LSTM) ağı, kapılı tekrarlayan birim (GRU), CNN-LSTM ve evrişimli LSTM (ConvLSTM) yöntemleri uygulanmıştır. Çeşitli sektörlere ait satış verileri kullanılarak deneysel çalışmalar gerçekleştirilmiştir. Hiperparametre optimizasyonu ardından ele alınan yöntemlerin performansları tahmin doğruluğu ve eğitim süreleri açısından karşılaştırılarak sonuçların istatistiksel anlamlılığı değerlendirilmiştir. Sonuç olarak, LSTM ve GRU modellerinin tahmin doğruluğunda başarılı sonuçlar verdiği, CNN modelinin ise eğitim süresini kısalttığı görülmüştür.

Anahtar Kelimeler

• Derin Öğrenme
• Satış Tahmini
• Zaman Serisi
• Evrişimli Sinir Ağı
• Tekrarlayan Sinir Ağı
• Uzun Kısa-Süreli Bellek Ağı

Comparison of Deep Learning Methods for Sales Forecasting

Öz

With the digital transformation, the importance of big data analytics in the supply chain management has been increasing day by day. Especially, the use of big data in fast and accurate estimation of customer demand provides companies competitive advantage. In this direction deep learning models, which is one of the artificial intelligence techniques, stand out in the discovery of complex patterns in big data. In the recent years, several deep learning methods have been proposed in the literature. In this study, the performances of deep learning methods for the sales forecasting problem are compared. In this context, deep neural network (DNN), deep autoencoder (DAE), convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory (LSTM) network, bidirectional LSTM (Bi-LSTM) network, gated recurrent unit (GRU), CNN-LSTM and convolutional LSTM (ConvLSTM) methods have been applied. Experimental studies were carried out using sales data from various sectors. After hyperparameter optimization, the performances of the methods discussed were compared in terms of forecasting accuracy and training time, and the statistical significance of the results was evaluated. As a result, it has been seen that LSTM and GRU models gave successful results in the prediction accuracy, and CNN model shortens the training time.

Anahtar Kelimeler

• Deep Learning
• Sales Forecasting
• Time Series
• Convolutional Neural Network
• Recurrent Neural Network
• Long Short-Term Memory Network

Kaynakça

1. Acı, M., and Doğansoy G. A. (2022) Demand forecasting for e-retail sector using machine learning and deep learning methods, Journal of the Faculty of Engineering and Architecture of Gazi University, 37(3), 1325-1339. doi: 10.17341/gazimmfd.944081
2. Belas, A., and Bidyuk, P. (2021) Convolutional neural networks for modeling and forecasting nonlinear nonstationary processes, ScienceRise, (3), 12-20. doi:10.21303/2313-8416.2021.001924
3. Bousqaoui, H., Slimani, I., and Achchab, S. (2021) Comparative analysis of short-term demand predicting models using ARIMA and deep learning, International Journal of Electrical & Computer Engineering, 2088-8708, 11(4). doi:10.11591/ıjece.v11ı4.pp3319-3328
4. Buyar, V., and Abdel-Raouf, A. (2019) A convolutional neural networks-based model for sales prediction, In Proceedings of the 2019 International Conference on Artificial Intelligence, Robotics and Control, 61-67. doi:10.1145/3388218.3388228
5. Chandriah K. K., Naraganahalli, R. V. (2021) RNN/LSTM with modified Adam optimizer in deep learning approach for automobile spare parts demand forecasting, Multimedia Tools and Applications, 1-15. doi:10.1007/s11042-021-10913-0
6. Cho, K., Van M. B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., and Bengio, Y. (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation, arXiv. doi:10.48550/arXiv.1406.1078
7. Chung, J., Gulcehre, C., Cho, K., and Bengio, Y. (2014) Empirical evaluation of gated recurrent neural networks on sequence modeling, arXiv. doi: 10.48550/arXiv.1412.3555
8. Demšar J. (2006) Statistical comparisons of classifiers over multiple data sets, The Journal of Machine Learning Research, 7, 1-30.

9. Dharshini MPA, and Vijila SA. (2021) Survey of machine learning and deep learning approaches on sales forecasting, In 2021 4th International Conference on Computing and Communications Technologies (ICCCT), 59-64. doi:10.1109/ICCCT53315.2021.9711878
10. Eglite, L., and Birzniece, I. (2022) Retail Sales Forecasting Using Deep Learning: Systematic Literature Review, Complex Systems Informatics and Modeling Quarterly, (30), 53-62. doi:10.7250/csimq.2022-30.03
11. Erol, B., and İnkaya, T. (2024) Satış tahmini için uzun kısa-süreli bellek ağı tabanlı derin transfer öğrenme yaklaşımı, Journal of the Faculty of Engineering and Architecture of Gazi University, 39(1), 191-202. doi:10.17341/gazimmfd.1089173
12. Gashler, M. S., and Ashmore, S. C. (2016) Modeling time series data with deep Fourier neural networks, Neurocomputing, 188, 3-11. doi:10.1016/j.neucom.2015.01.108
13. Graves, A., and Schmidhuber, J. (2005) Framewise phoneme classification with bidirectional LSTM and other neural network architectures, Neural networks, 18(5-6), 602-610. doi:10.1016/j.neunet.2005.06.042
14. Goodfellow, I., Bengio, Y., and Courville, A. (2016) Deep learning, USA: MIT Press, Vol 1.
15. Greff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R., and Schmidhuber, J. (2016) LSTM: A search space odyssey, IEEE transactions on neural networks and learning systems, 28(10), 2222-2232. doi:10.1109/TNNLS.2016.2582924
16. Hochreiter, S., and Schmidhuber, J. (1997) LSTM can solve hard long time lag problems, Advances in neural information processing systems, 473-479.
17. Iman, R. L., Davenport, J. M. (1980) Approximations of the critical region of the fbietkan statistic, Communications in Statistics-Theory and Methods, 9(6), 571-595. doi:10.1080/03610928008827904
18. Ingle, C., Bakliwal, D., Jain, J., Singh, P., Kale, P., and Chhajed, V. (2021) Demand forecasting: Literature review on various methodologies, In 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), 1-7. doi:10.1109/ICCCNT51525.2021.9580139
19. Jiang, L., Rollins, K. M., Ludlow, M., and Sadler, B. (2020) Demand forecasting for alcoholic beverage distribution, SMU Data Science Review, 3(1), 5.
20. Kaggle, (2020). https://www.kaggle.com/datasets (Erişim tarihi: 5.10.2020).
21. Kingma, D. P., and Ba, J. (2014) Adam: A method for stochastic optimization, arXiv. doi:10.48550/arXiv.1412.6980
22. Kiranyaz, S., Avci, O., Abdeljaber, O., Ince, T., Gabbouj, M., and Inman, D. J. (2021) 1D convolutional neural networks and applications: A survey, Mechanical systems and signal processing, 151, 107398. doi:10.1016/j.ymssp.2020.107398
23. LeCun, Y., Bengio, Y., and Hinton, G. (2015) Deep learning, nature, 521(7553), 436-444.
24. Liu, Y., Lan, K., Huang, F., Cao, X., Feng, B., and Zhu, B. (2021) An aggregate store sales forecasting framework based on ConvLSTM, In 2021 The 5th International Conference on Compute and Data Analysis, 67-72. doi:10.1145/3456529.3456540
25. Muhaimin, A., Prastyo, D. D., and Lu, H. H. S. (2021) Forecasting with recurrent neural network in intermittent demand data, In 2021 11th International Conference on Cloud Computing, Data Science & Engineering (Confluence), 802-809. doi: 10.1109/Confluence51648.2021.9376880
26. Pacella, M., and Papadia, G. (2021) Evaluation of deep learning with long short-term memory networks for time series forecasting in supply chain management, Procedia CIRP, 99, 604-609. doi:10.1016/j.procir.2021.03.081
27. Peköz, A. Z., and İnkaya, T. (2023) Derin öğrenme ile talep tahmini: Bir üçüncü parti lojistik firması için COVID-19 döneminde vaka analizi, Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 24(4), 705-712. doi:10.5505/pajes.2022.73537
28. Puspita, P. E., İnkaya, T., and Akansel, M. (2019) Clustering-based sales forecasting in a forklift distributor, International Journal of Engineering Research and Development, 11 (1), 25-40. doi:10.29137/umagd.473977
29. Qi, Y., Li, C., Deng, H., Cai, M., Qi, Y., and Deng, Y. (2019) A deep neural framework for sales forecasting in e-commerce, In Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 299-308. doi:10.1145/3357384.3357883
30. Ren, S., Choi, T. M., Lee, K. M., and Lin, L. (2020) Intelligent service capacity allocation for cross-border-E-commerce related third-party-forwarding logistics operations: A deep learning approach, Transportation Research Part E: Logistics and Transportation Review, 134, 101834. doi:10.1016/j.tre.2019.101834
31. Rizvi, S. M., Syed, T., and Qureshi, J. (2021) Real-time forecasting of petrol retail using dilated causal CNNs, Journal of Ambient Intelligence and Humanized Computing, 1-12. doi:10.1007/s12652-021-02941-3
32. Sarker, I. H. (2021) Deep learning: A comprehensive overview on techniques, taxonomy, applications and research directions, SN Computer Science, 2(6), 420. doi:10.1007/s42979-021-00815-1
33. Wang, J., Yu, L. C., Lai, K. R., and Zhang, X. (2016) Dimensional sentiment analysis using a regional CNN-LSTM model, In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Volume 2: Short Papers, 225-230.
34. Wang, J., Liu G. Q., and Liu, L. (2019) A selection of advanced technologies for demand forecasting in the retail industry, In 2019 IEEE 4th International Conference on Big Data Analytics (ICBDA), 317-320. doi:10.1109/ICBDA.2019.8713196
35. Wang, S., Jiang, Y., Hou, X., Cheng, H., and Du, S. (2017) Cerebral micro-bleed detection based on the convolution neural network with rank based average pooling, IEEE Access, 5, 16576-16583. doi:10.1109/ACCESS.2017.2736558
36. Wang, T., Li, L., and Huang, W. (2020) Research on the construction of sales forecasting model of fashion products based on feature representation of multimodal and deep learning, WHICEB 2020 Proceedings, 33.
37. Xingjian, S. H. I., Chen, Z., Wang, H., Yeung, D. Y., Wong, W. K., and Woo, W. C. (2015) Convolutional LSTM network: A machine learning approach for precipitation nowcasting, In Advances in neural information processing systems, 28, 802-810.