Journal of Korean Society of Industrial and Systems Engineering (산업경영시스템학회지)

Society of Korea Industrial and System Engineering (한국산업경영시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Development of the Demand Forecasting and Product Recommendation Method to Support the Small and Medium Distribution Companies based on the Product Recategorization

중소유통기업지원을 위한 상품 카테고리 재분류 기반의 수요예측 및 상품추천 방법론 개발

  • Sangil Lee (Digital Convergence Research Laboratory, Air Mobility Research Division, Postal & Logistics Technology Research Center, Electronics and Telecommunications Research Institute) ;
  • Yeong-WoongYu (Digital Convergence Research Laboratory, Air Mobility Research Division, Postal & Logistics Technology Research Center, Electronics and Telecommunications Research Institute) ;
  • Dong-Gil Na (Digital Convergence Research Laboratory, Air Mobility Research Division, Postal & Logistics Technology Research Center, Electronics and Telecommunications Research Institute)
  • 이상일 (한국전자통신연구원 디지털융합연구소 에어모빌리티연구본부 우정.물류기술연구센터) ;
  • 유영웅 (한국전자통신연구원 디지털융합연구소 에어모빌리티연구본부 우정.물류기술연구센터) ;
  • 나동길 (한국전자통신연구원 디지털융합연구소 에어모빌리티연구본부 우정.물류기술연구센터)
  • Received : 2024.05.10
  • Accepted : 2024.06.12
  • Published : 2024.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Distribution and logistics industries contribute some of the biggest GDP(gross domestic product) in South Korea and the number of related companies are quarter of the total number of industries in the country. The number of retail tech companies are quickly increased due to the acceleration of the online and untact shopping trend. Furthermore, major distribution and logistics companies try to achieve integrated data management with the fulfillment process. In contrast, small and medium distribution companies still lack of the capacity and ability to develop digital innovation and smartization. Therefore, in this paper, a deep learning-based demand forecasting & recommendation model is proposed to improve business competitiveness. The proposed model is developed based on real sales transaction data to predict future demand for each product. The proposed model consists of six deep learning models, which are MLP(multi-layers perception), CNN(convolution neural network), RNN(recurrent neural network), LSTM(long short term memory), Conv1D-BiLSTM(convolution-long short term memory) for demand forecasting and collaborative filtering for the recommendation. Each model provides the best prediction result for each product and recommendation model can recommend best sales product among companies own sales list as well as competitor's item list. The proposed demand forecasting model is expected to improve the competitiveness of the small and medium-sized distribution and logistics industry.

Keywords

Acknowledgement

This work supported by Digital distribution logistics technology development and demonstration support funded by the Ministry of the Trade, Industry and Energy of Korea(MOTIE, Korea). [Project Name: Development of product recommendation technology using big data for small and medium distribution companies / Project Number: 1415184128]

References

  1. Acilar, A.M. and Arslan, A., A Collaborative Filtering Method Based on Artificial Immune Network, Expert Systems with Applications, 2009 Vol. 36, No. 4, pp.8324-8332.
  2. Adomavicius, G. and Tuzhilin, A., Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-art and Possible Extensions, IEEE Transactions on Knowledge and Data Engineering, 2005, Vol. 17, No. 6, pp. 734-749.
  3. Baik, J., Chung, S., and Chi, S., Issue Identification of Overseas Construction Markets from News Articles Based on BERTopic, Journal of Construction Automation and Robotics, 2023, Vol. 2, No. 2, pp. 21-26.
  4. Bandara, K. Bergmeir, C. and Smyl, S., Forecasting Across Time Series Databases using RNNs on Groups of Similar Series: A Clustering Approach, arXiv [cs.LG], 2017, pp. 1-33. https://doi.org/10.48550/arXiv.1710.03222.
  5. Bandara, K., Shi, P., Bergmeir, C., Hewamalage, H., Tran, Q., and Seaman, B., Sales Demand Forecast in E-commerce Using a Long Short-Term Memory Neural Network Methodology. In: Gedeon, T., Wong, K., Lee, M. (eds), Neural Information Processing, ICONIP 2019. Lecture Notes in Computer Science, 2019, Vol. 11955.
  6. Barrow, D.K. and Crone, S.F., A Comparison of AdaBoost Algorithms for Time Series Forecast Combination, International Journal of Forecasting, 2016, Vol. 32, No. 4, pp.1103-1119.
  7. Borovykh, A., Bohte, S., and Oosterlee, C.W., Conditional Time Series Forecasting with Convolutional Neural Networks, arXiv [cs.AI], 2017, pp. 1-22. https://doi.org/10.48550/arXiv.1703.04691.
  8. Cha, H.C., A Big Data Analysis for Demand Forecasting of Multi-variety Small-volume Sales Environment-Focusing on a Case of Selling Electronic Parts, Journal of Korea Multimedia Society, 2022, Vol. 25, No. 12, pp. 1681-1688.
  9. Chapados, N., Effective Bayesian Modeling of Groups of Related Count Time Series, Proceedings of the 31st International Conference on Machine Learning in Proceedings of Machine Learning Research, 2014, Vol. 32, No.2, pp.1395-1403. https://proceedings.mlr.-press/v32/chapados14.html.
  10. Du, S., Wang, J., Wang, M., Yang, J., Zhang, C., Zhao, Y., and Song, H., A Systematic Data-driven Approach for Production Forecasting of Coalbed Methane Incorporating Deep Learning and Ensemble Learning Adapted to Complex Production Patterns, Energy, 2023, Vol. 263, Part E, No. 15, p. 126121.
  11. George, E.P.B., Gwilym, M.J., Gregory, C.R., and Greta, M.L., Time Series Analysis: Forecasting and Control, Wiley, Hoboken, 2015.
  12. Grootendorst, M.R., BERTopic: Neural Topic Modeling with a Class-based TF-IDF Procedure, ArXiv, abs/2203.05794, 2022, pp. 1-10. https://doi.org/10.48550/arXiv.2203.05794
  13. Han, K., Yu, Y., Na, D., Jung, H., Heo, Y., Jeong, H., Yun, S., and Kim, J., Understanding Postal Delivery Areas in the Republic of Korea using Multiple Unsupervised Learning Approaches, ETRI Journal, 2022, Vol. 44, No. 2, pp. 333-351.
  14. Hyndman, R., Koehler, A., Ord, K., and Snyder, R., Forecasting with Exponential Smoothing: The State Space Approach, Springer, Heidelberg, 2008.
  15. Isinkaye, F.O., Folajimi. Y.O., and Ojokoh, B.A., Recommendation Systems: Principles, Methods, and Evaluation, Egyptian Informatics Journal, 2015, Vol. 16, No. 3, pp. 261-273.
  16. Ju, C., Bibaut, A., and Van Der Laan, M., The Relative Performance of Ensemble Methods with Deep Convolutional Neural Networks for Image Classification, Journal of Applied Statistics, 2018, Vol. 45, No. 15, pp.2800-2818.
  17. KCCI, Korea 2023 Distribution Logistics Statistics Collection, Korea Chamber of Commerce and Industry, 2023. (Last accessed at: 24.04.24, www.korcham.net)
  18. Kim, H., Ryu, G., Cai, J., and Son, H., A Study on the AI Model for Prediction of Demand for Cold Chain Distribution of Drugs, The Journal of the Convergence on Culture Technology (JCCT), 2023, Vol. 9, No. 3, pp. 763-768.
  19. Kim, Y.N., Ryu, S.C., and Kim, H., A Study on Demand Forecasting Method for Optimal Operation of the Fulfillment Center, Journal of The Institute of Electronics and Information Engineers, 2023, Vol. 60, No. 4, pp. 466-471.
  20. Koren, Y., Rendle, S., and Bell, R. (2022). Advances in Collaborative Filtering. In: Ricci, F., Rokach, L., Shapira, B. (eds), Recommender Systems Handbook. Springer, New York, NY. https://doi.org/10.1007/978-1-0716-2197-4_3.
  21. Lee, K.H. Bang, S.H. Young, J.J. and Shin, K.S., Demand Forecasting Model Development using Machine Learning - Case of Mongolian Retail Company, Korea Logistics Review, 2022, Vol. 32, No. 6, pp. 111-120.
  22. Lee, W.C., Toon, H.S., and Jeong, S.B., Collaborative Filtering for Credit Card Recommendation Based on Multiple User Profiles, Journal of Society of Korea Industrial and Systems Engineering, 2017, Vol. 40, No. 4, pp. 154-163.
  23. McKinsey and Company, Notes form The AI Frontier Insights from Hundreds of Use Case, McKinsey Global Institute, 2018, pp. 1-36.
  24. Pu, P., Chen, L., and Hu, R., A User-centric Evaluation Framework for Recommender Systems, Proceedings of the fifth ACM conference on Recommender Systems (RecSys '11), ACM, New York, NY, USA, 2011, pp.57-164.
  25. Ramachandran, P., Zoph, B., and Le, Q.V., Searching for Activation Functions, arXiv preprint arXiv:1710.05941, 2017, pp. 1-13. https://doi.org/10.48550/arXiv.1710.05941.
  26. Salinas, D., Flunkert, V., Gasthaus, J., and Januschowski, T., DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks, International Journal of Forecasting, 2017, Vol. 36, No. 3, pp. 1181-1191.
  27. Seyedan, M., Mafakheri, F., and Wang, C., Order-to-level Inventory Optimization Model using Time-series Demand Forecasting with Ensemble Deep Learning, Supply Chain Analytics, 2023, Vol. 3, pp.100024.
  28. Statistics Korea, Trend of Service Industry at 2023, Statistics Korea, 2023 (last accessed at 24.04.24, www.index.go.kr).
  29. Trapero, J.R., Kourentzes, N., and Fildes, R., On the Identification of Sales Forecasting Models in the Presence of Promotions, Journal of the Operational Research Society, 2015, Vol. 66, pp. 299-307.
  30. Wen, R., Torkkola, K., Narayanaswamy, B., and Madeka, D., A Multi-horizon Quantile Recurrent Forecaster, arXiv [stat.ML], 2017, pp. 1-9. https://doi.org/10.48550/arXiv.1711.11053.
  31. Yoo, S.Y., Yoon, S.G., and Park, M.Y., Determining Optimal Data Structure for Improving Demand Forecasting Accuracy, Journal of Distribution and Logistics, 2022, Vol. 9, No. 4, pp. 5-17.