Developing Demand Forecasting Models for E-Commerce: Analyzing the Impact of Time Lags on Model Performance

Abstract

Time series are an important analytical tool used in many problems today. Particularly favored in regression problems such as demand forecasting, time series enable more accurate modeling of the impact of past data on future values through various lag options. Time lag is a method used in time series analysis or machine learning models to examine the effect of past (lagged) values of a variable on current or future values. Time lag options play a crucial role, particularly in the success of demand forecasts. This study aims to develop demand forecasting models that help e-commerce businesses gain a competitive advantage by accurately predicting demand and comprehensively analyzing the impact of time delay options on forecasting performance. In this context, an interface with hyperparametric flexibility has been developed, and the effects of the lag options "Use Best N," "Use Correlation," "Use All Delays," and "Selected Delay Lag" on forecasting performance have been analyzed using demand forecasting models. Models have been created for two different months and three different products. The performance of the developed models has been evaluated using the Mean Absolute Percentage Error (MAPE) metric. The lowest MAPE value for July has been obtained with the MQRNN model developed using product A, while the lowest MAPE value for August has been obtained with the MLP model developed using product B.

Keywords

• Time-lag Options
• E-Commerce
• Demand Forecasting
• Machine learning

References

1. Gong, K., Peng, Y., Wang, Y., & Xu, M. (2018). Time series analysis for C2C conversion rate. Electronic Commerce Research, 18, 763-789.
2. Akadji, A. F., & Dewantara, R. (2024). Big Data Analysis for Product Demand Prediction in Indonesian E-commerce. West Science Information System and Technology, 2(01), 9-17.
3. Nussipova, F., Rysbekov, S., Abdiakhmetova, Z., & Kartbayev, A. (2024). Optimizing loss functions for improved energy demand prediction in smart power grids. International Journal of Electrical & Computer Engineering (2088-8708), 14(3).
4. Rasul, K., Ashok, A., Williams, A. R., Ghonia, H., Bhagwatkar, R., Khorasani, A., Darvishi Bayazi, M. J., Adamopoulos, G., Riachi, R., Hassen, N., Biloš, M., Garg, S., Schneider, A., Chapados, N., Drouin, A., Zantedeschi, V., Nevmyvaka, Y., & Rish, I. (2024). Lag-Llama: Towards foundation models for probabilistic time series forecasting. arXiv(Preprint). https://doi.org/10.48550/arXiv.2310.08278
5. Peláez-Rodríguez, C., Pérez-Aracil, J., Fister, D., Torres-López, R., & Salcedo-Sanz, S. (2024). Bike sharing and cable car demand forecasting using machine learning and deep learning multivariate time series approaches. Expert Systems with Applications, 238, 122264.
6. Khatun, A., Nisha, M. N., Chatterjee, S., & Sridhar, V. (2024). A novel insight on input variable and time lag selection in daily streamflow forecasting using deep learning models. Environmental Modelling & Software, 179, 106126.
7. Guo, J. (2024, May). Commodity Demand Forecasting of E-Commerce Merchants Based on the Stacking Fusion Model. In 2024 6th International Conference on Communications, Information System and Computer Engineering (CISCE) (pp. 1036-1040). IEEE.
8. Li, C. (2024). Commodity demand forecasting based on multimodal data and recurrent neural networks for E-commerce platforms. Intelligent Systems with Applications, 22, 200364.

9. Li, J., Fan, L., Wang, X., Sun, T., & Zhou, M. (2024). Product Demand Prediction with Spatial Graph Neural Networks. Applied Sciences, 14(16), 6989.
10. Liu, J., Wu, T., Wu, J., Chen, Z., Gong, J., & Chi, H. (2024). Forecasting Analysis of Demand for Agricultural Products in E-Commerce Based on Single Forecasting Model. In Artificial Intelligence Technologies and Applications (pp. 479-489). IOS Press.
11. Liu, J., Wu, T., Wu, J., Chen, Z., Gong, J., & Chi, H. (2024). Combinatorial Model-Based Demand Forecast Analysis of E-Commerce Agricultural Products. In Artificial Intelligence Technologies and Applications (pp. 508-516). IOS Press.
12. Liu, Z., Zhao, Y., Yang, S., Ju, J., Yang, L., Li, R., ... & Lu, W. (2024). Time Series Analysis of Product Demand Forecasting and Inventory Optimization on E-commerce Platforms. Journal of Electronics and Information Science, 9(1), 49-54.
13. Lv, J. (2024, February). Research on Inventory Management and Demand Forecasting of E-commerce Platform Based on ARIMA and LSTM Models. In 2024 IEEE 3rd International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA) (pp. 494-499). IEEE.
14. Trisolvena, M. N., Masruroh, M., & Ginting, Y. M. (2024). Product Demand Forecast Analysis Using Predictive Models and Time Series Forecasting Algorithms on the Temu Marketplace Platform. International Journal Software Engineering and Computer Science (IJSECS), 4(2), 430-439.
15. Zhang, J., Zhang, Y., Tang, F., Song, Y., Deng, Y., & He, S. (2024, May). E-commerce Retail Merchandise Based on Optimized K-means Algorithm and Multi-model Fusion Demand Forecasting Research. In Proceedings of the 2024 International Conference on Smart City and Information System (pp. 512-516).
16. Zhao, Y. (2024). Research on E-Commerce Retail Demand Forecasting Based on SARIMA Model and K-means Clustering Algorithm. Academic Journal of Science and Technology, 10(3), 226-231.
17. Xu, Z., Zhang, L., Yang, S., Etesami, R., Tong, H., Zhang, H., & Han, J. (2024). F-FOMAML: GNN-enhanced meta-learning for peak period demand forecasting with proxy data. arXiv(Preprint). https://doi.org/10.48550/arXiv.2406.16221
18. Wang, G., Gao, J., Shao, S., & Dong, Y. (2024, February). Platform Merchant Demand Prediction Based on Decision Tree and Multi-Layer Perceptron Models. In 2024 IEEE 3rd International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA) (pp. 995-1000). IEEE.
19. Aravazhi, A. (2021). Hybrid machine learning models for forecasting surgical case volumes at a hospital. AI, 2(4), 512-526.
20. Zhang, X. Y., Watkins, C., & Kuenzel, S., Multi-quantile recurrent neural network for feeder-level probabilistic energy disaggregation considering roof-top solar energy. Engineering Applications of Artificial Intelligence, 110, 104707, 2022.
21. Fırat, A. T., Aygün, O., Göğebakan, M., Akay, M. F., & Ulus, C. Development of machine learning based demand forecasting models for the e-commerce sector. Uluslararası Mühendislik Tasarım ve Teknoloji Dergisi, 7(1), 13-20. https://doi.org/10.70669/ijedt.1567739