Comparative Performance Analysis of Multilayer Perceptron and Long Short-Term Memory for Daily Demand Forecasting in E-Commerce Delivery Platforms

Ica Unari; Martanto; Raditya Danar  Dana; Ahmad Rifa'i; Ryan  Hamongan

doi:10.59934/jaiea.v5i2.1846

Authors

Ica Unari STMIK IKMI Cirebon
Martanto STMIK IKMI Cirebon
Raditya Danar Dana STMIK IKMI Cirebon
Ahmad Rifa'i STMIK IKMI Cirebon
Ryan Hamongan STMIK IKMI Cirebon

DOI:

https://doi.org/10.59934/jaiea.v5i2.1846

Keywords:

Daily demand forecasting, Deep learning, E-commerce, Long Short-Term Memory, Multilayer Perceptron

Abstract

This study compares the performance of two deep learning architectures—Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM)—for daily demand forecasting on an e-commerce delivery platform. The dataset consists of 1,827 daily observations from 2020 to 2024 and includes operational, temporal, and behavioral features such as holiday indicators, promotion signals, active customers, and delivery time. Data preprocessing includes cleaning, feature engineering, scaling, and sequence generation using a 30-day sliding window. Both models were trained and evaluated using consistent experimental settings and performance metrics. The results show that the LSTM model achieves better accuracy than the MLP model, with an RMSE of 811.81 compared to 830.15, while the difference in MAE between the two models remains minimal. LSTM demonstrates superior capability in capturing temporal dependencies and reacting to rapid demand fluctuations, whereas both models face challenges when predicting sudden demand spikes. These findings indicate that memory-based models such as LSTM are more effective for highly volatile time-series forecasting in e-commerce operations. However, performance can be further improved with the addition of external variables such as real-time promotions, weather conditions, and multivariate features.

Downloads

Download data is not yet available.

References

J. A. Cano, A. Londoño-Pineda, and C. Rodas, “Sustainable logistics for e-commerce: A literature review and bibliometric analysis,” Sustainability, vol. 14, no. 19, p. 12247, 2022, doi: 10.3390/su141912247.

D. Karl, “Forecasting e-commerce consumer returns: A systematic literature review,” Manag. Rev. Q., 2024, doi: 10.1007/s11301-024-00436-x.

M. Markowska, J. Marcinkowski, M. Kiba-Janiak, and D. Strahl, “Rural e-customers’ preferences for last mile delivery and products purchased via the Internet before and after the COVID-19 pandemic,” J. Theor. Appl. Electron. Commer. Res., vol. 18, no. 1, pp. 597–614, 2023, doi: 10.3390/jtaer18010030.

M. Suguna, B. Shah, S. K. Raj, and M. Suresh, “A study on the influential factors of the last-mile delivery projects during COVID-19 era,” Oper. Manag. Res., vol. 15, pp. 399–412, 2022, doi: 10.1007/s12063-021-00214-y.

S. F. Ni, Y. Peng, and Z. J. Liu, “Logistics demand forecast of fresh food e-commerce based on Bi-LSTM model,” J. Comput. Commun., vol. 10, pp. 51–65, 2022, doi: 10.4236/jcc.2022.109004.

M. Nasseri, T. Falatouri, P. Brandtner, and F. Darbanian, “Applying Machine Learning in Retail Demand Prediction—A Comparison of Tree-Based Ensembles and Long Short-Term Memory-Based Deep Learning,” Appl. Sci., vol. 13, no. 19, p. 11112, 2023, doi: 10.3390/app131911112.

K. Douaioui, R. Oucheikh, O. Benmoussa, and C. Mabrouki, “Machine Learning and Deep Learning Models for Demand Forecasting in Supply Chain Management: A Critical Review,” Appl. Syst. Innov., vol. 7, no. 5, p. 93, 2024, doi: 10.3390/asi7050093.

C. Kaoutar Douaioui, Rachid Oucheikh, Othmane Benmoussa, “Model pembelajaran mesin dan pembelajaran mendalam untuk peramalan permintaan dalam manajemen rantai pasok: Tinjauan kritis,” Appl. Syst. Innov., vol. 7, no. 5, p. 93, 2024, doi: 10.3390/asi7050093.

Nasseri, “Nasseri, M., Falatouri, T., Brandtner, P., & Darbanian, F. (2023). Penerapan Pembelajaran Mesin dalam Prediksi Permintaan Ritel—Perbandingan antara Ensembel Berbasis Pohon dan Pembelajaran Mendalam Berbasis LSTM. Applied Sciences, 13(19), 11112. https://d”.

E. Aldahmani, A. Alzubi, and K. Iyiola, “Demand Forecasting in Supply Chain Using Uni-Regression Deep Approximate Forecasting Model,” Appl. Sci., vol. 14, no. 18, p. 8110, 2024, doi: 10.3390/app14188110.

J.-J. Zhou, “An improved machine learning model Shapley value-based to forecast demand for aquatic product supply chain,” Front. Ecol. Evol., 2023, doi: 10.3389/fevo.2023.1160684.

R. Baidya and S.-W. Lee, “Addressing the non-stationarity and complexity of time series data for long-term forecasts,” Appl. Sci., vol. 14, no. 11, p. 4436, 2024, doi: 10.3390/app14114436.

X. Kong, Z. Chen, W. Liu, K. Ning, and L. Zhang, “Deep learning for time series forecasting: A survey,” Int. J. Mach. Learn. Cybern., vol. 16, pp. 5079–5112, 2025, doi: 10.1007/s13042-025-02560-w.

P. Lara-Benítez, M. Carranza-García, and J. C. Riquelme, “An experimental review on deep learning architectures for time series forecasting,” 2021. [Online]. Available: https://arxiv.org/abs/2103.12057

W. Li and K. E. Law, “Model pembelajaran mendalam untuk peramalan deret waktu: Sebuah tinjauan,” IEEE Access, vol. 11, pp. 71234–71244, 2023, doi: 10.1109/ACCESS.2023.3167042.

V. Kuppulakshmi, C. Sugapriya, D. Nagarajan, and A. Kanchana, “Modelling with neural networks and time-series forecasting: inventory control and cost reduction in supply chain process,” SN Oper. Res., vol. 6, no. 2, 2025, doi: 10.1007/s43069-025-00466-5.

W. Yang, “A neural network-based model for cross-border e-commerce supply chain demand forecasting and inventory optimization,” Appl. Math. Nonlinear Sci., vol. 9, no. 1, 2024, doi: 10.2478/amns-2024-2915.

X. Liu and W. Wang, “Model pembelajaran mendalam untuk peramalan deret waktu: Sebuah survei komprehensif,” Mathematics, vol. 12, no. 10, p. 1504, 2024, doi: 10.3390/math12101504.

A. Hussain and K. Ahsan, “Hybrid EEMD-LSTM model for accurate e-commerce demand forecasting,” J. Data Digit. Innov., vol. 2, no. 2, 2025.