Keywords
Random forest
Bayesian optimization
Adaptive algorithm
Submitted : 2026-05-30
Accepted : 2026-06-14
Published : 2026-06-29
Abstract
Due to the characteristics of e-commerce sales data—high dimensionality, diverse types, and nonlinear relationships—traditional models exhibit insufficient adaptability. This study aims to construct a deep ensemble prediction model to provide scientific support for enterprise inventory and marketing decisions. The model integrates convolutional neural networks (CNN) with an improved weighted deep forest (WDF). A multi-granularity scanning mechanism enhances perception of local spatiotemporal features; a binary adaptive differential evolution algorithm dynamically selects key features; and Bayesian optimization precisely tunes model hyperparameters. Experiments are conducted using large-scale data from mainstream e-commerce platforms. Results show that the model achieves a mean absolute percentage error (MAPE) of only 6.8% on the test set, outperforming baseline models such as ARIMA, random forest, and XGBoost in capturing nonlinear trends and long-term dependencies. This adaptive ensemble model effectively addresses feature redundancy and model mismatch issues, significantly improving the stability of sales prediction and providing reliable technical support for precise e-commerce operations.
References
Xun K, Feng B, Chen Y, et al., 2022., Integrated Learning Method for Thymoma CT Image Prediction Combining Deep Learning and Improved Extreme Learning Machine. Computer Science, 2022(49): 455–460.
Liu L, Chen X, Sun S, et al., 2022, Application of Deep Learning in Drug Activity Prediction Research. Progress in Biochemistry and Biophysics, 2022(49): 110–131.
Li M, Sheng K, Xiong Z, et al., 2025, Research on the Application of Deep Learning in Plastic Processing. Plastics Industry, 53(462): 209–210.
Zhang Y, Yu Q, Zhang L, 2024, User Purchase Intention Prediction based on Evolutionary Ensemble Learning. Application Research of Computers, 41(388): 54–60.
Yuan R, Wei H, Fu Z, et al., 2025, Research on E-Commerce Product Sales Prediction Fusing CNN and WDF Models. Computer Engineering and Applications, 61(1065): 339–347.
Huang H, Sheng W, 2022, Click Prediction Model based on Product Description Copy. Application Research of Computers, 39(370): 188–192.
Zhou F, Chen X, Zhong T, 2022, A Survey of Deep Learning Techniques for Financial Technology. Computer Science, 2022(49): 20–36.
Yan Y, Huang Q, Li N, 2023, Research on Feature Selection and Efficient Disease Early Warning based on Optimized Ensemble Learning Models: A Case Study of Geriatric Depression and Anxiety. Data Analysis and Knowledge Discovery, 7(79): 78–92.
Li N, Liu W, Meng F, 2022, Spatiotemporal Regional Economic Visualization Application Under Telecom Big Data Analysis. Journal of Beijing University of Aeronautics and Astronautics, 48(348): 84–92.
Dang H, Wang Z, Zhao D, et al., 2024, Prediction of Plate Boundary Earthquakes in the Japan Subduction Zone based on Stacking Model Fusion Strategy. World Earthquake Engineering, 2024(40): 82–97.
Guo Z, Ma B, Zhang S, et al., 2024, Research Progress and Technical Outlook of Deep Learning in Oil and Gas Production Prediction. Natural Gas Industry, 44(371): 94–104.
Chen Z, Hong Y, Chen T, et al., 2025, Rapid Prediction Model for Tunnel Fire Smoke Layer Height and Back-Layering Length based on Transposed Convolutional Neural Networks. China Occupational Safety Science and Technology, 2025(21): 65–70.
Gong C, Li Y, Liu J, et al., 2023, Rapid Automatic Adjustment Method for Large Power Grid Section Power based on Deep Learning. Automation of Electric Power Systems, 47(744): 186–195.
Ren N, Fu Y, Wu Y, et al., 2022, Survey of Research on Imbalance Problems in Deep Learning for Object Detection. Computer Science and Exploration, 16(168): 5–25.
Liu R, Luo K, Xing J, et al., 2022, A Neural Network-Based Combustion Model and its a Priori Validation. Combustion Science and Technology, 28(152): 75–81.
Jiang K, Xie Y, Li M, et al., 2024, Research on Predicting Knee Osteoarthritis Onset using 3D Convolutional Neural Network Models based on Meniscus MRI. Chinese Journal of Magnetic Resonance Imaging, 15(140): 110–114+128.