Library

Short-Term Demand Forecast of E-Commerce Platform Based on ConvLSTM Network

Based on real sales data, this article constructed LGBM and LSTM sales prediction models to compare and verify the performance of the proposed models. In this article, we forecast the product sales of stores in the future T + 3 days and use MAPE as the evaluation index. The experiment shows that the product sales prediction model based on the convolutional LSTM (ConvLSTM) network has better prediction accuracy. From a store point of view, ConvLSTM prediction model MAPE was 0.42 lower than the long short-term memory (LSTM) network and 0.68 lower than LGBM. From the perspective of commodity categories, different commodity categories are suitable for different forecasting methods. Some categories are suitable for regression forecasting, while others are suitable for time-series forecasting. Among the categories suitable for time-series forecasting, the ConvLSTM model performs the best.

Computer ScienceBusinessMedicine
View graphSource

Paper

Full text

PDF

Short-Term Demand Forecast of E-Commerce Platform Based on ConvLSTM Network

Semantic Scholar · Computer Science · 2022

Abstract

Based on real sales data, this article constructed LGBM and LSTM sales prediction models to compare and verify the performance of the proposed models. In this article, we forecast the product sales of stores in the future T + 3 days and use MAPE as the evaluation index. The experiment shows that the product sales prediction model based on the convolutional LSTM (ConvLSTM) network has better prediction accuracy. From a store point of view, ConvLSTM prediction model MAPE was 0.42 lower than the long short-term memory (LSTM) network and 0.68 lower than LGBM. From the perspective of commodity categories, different commodity categories are suitable for different forecasting methods. Some categories are suitable for regression forecasting, while others are suitable for time-series forecasting. Among the categories suitable for time-series forecasting, the ConvLSTM model performs the best.

Source of record · Semantic Scholar

Similar papers

Sales forecasting using multivariate long short term memory network modelsSuleka Helmini, Nadheesh Jihan, Malith Jayasinghe et al.2019 · PeerJ Preprints · 32 citations In Library
Sales Demand Forecast in E-commerce using a Long Short-Term Memory Neural Network MethodologyKasun Bandara, Peibei Shi, C. Bergmeir et al.2019 · International Conference on Neural Information Processing · 168 citations In Library
LSTM-Based Consumer Behavior Prediction Model ResearchShuhan Chen, Wenci Tan2025 In Library
Demand Forecasting using Long Short-Term Memory Neural NetworksMarta Golabek, Robin Senge, R. Neumann2020 · arXiv.org · 5 citations In Library
Research on sales Forecast based on XGBoost-LSTM algorithm ModelHe Wei, Qingtao Zeng2021 · Journal of Physics: Conference Series · 21 citations In Library
A PREDICTION MODEL OF USER BUYING BEHAVIOR BASED ON LSTM AND SVMXue Bingbing, Jitao Zhao, Wei Xianyi2021 In Library
Statistical and Machine Learning-based E-commerce Sales ForecastingWen-Li Dong, Qingming Li, H.Vicky Zhao2019 · International Conference on Crowd Science and Engineering · 8 citations In Library
Food Product Sales Forecasting Using the LSTM Model: A Case Study of SMAN 1 Malang Teachers’ CooperativeAchmad Aries Nazali, Vivi Aida Fitria2026 · ICoBITS In Library
Demand forecasting of products using deep learning: A focus on long short-term memory systemsSana Amreen, Tahura Siddiqua, Shaik Mohd et al.2025 In Library
Prediction based on traditional network prediction model and LSTM deep neural network modelHuiling Li, Daijun Wei2023 · International Conferences on Computing, Networks and Internet of Things · 3 citations In Library
© 2026 NYSGPT2525 LLC