Academic Journal of Business & Management, 2024, 6(11); doi: 10.25236/AJBM.2024.061138.
Yiping Wang1, Zhishan Ren2
1Internet of Things Engineering, University of South China, Hengyang, 421001, China
2Mathematics and Applied Mathematics, Xi'an University of Science and Technology, Xi'an, 710600, China
Over the last few years, the widespread adoption of various 4G and 5G networks, along with residents' acceptance of innovative online shopping methods, has positioned e-commerce as a primary operational model for numerous businesses. Accurate forecasting in e-commerce has become a crucial foundation for informed business decisions. This paper presents a system model that analyzes the factors influencing online sales, such as customer unit price, user page views, and transaction conversion rates. Additionally, the training error curve and correlation coefficient curve are generated using the BP neural network prediction model. The results indicate a correlation coefficient of 0.99804, a mean squared error of 0.0021458, an average absolute error of 0.0035446, and a minimal relative error of 0.0034991. These findings suggest that the forecasting results are highly accurate, enabling enterprises to develop more effective sales strategies and enhance their online marketing performance.
Business Decision, E-commerce Sales, BP Neural Network, Sales Forecasting
Yiping Wang, Zhishan Ren. Research on e-commerce sales forecast based on BP neural network. Academic Journal of Business & Management (2024) Vol. 6, Issue 11: 262-268. https://doi.org/10.25236/AJBM.2024.061138.
[1] Cheng Qiyun, Sun Caixin, Zhang Xiaoxing, et al. Short-Term load forecasting model and method for power system based on complementation of neural network and fuzzy logic [J]. Transactions of China Electrotechnical Society, 2004, 19(10): 53-58.
[2] Fang fang. Research on power load forecasting based on Improved BP neural network [D]. Harbin Institute of Technology, 2011.
[3] Amjady N. Short-term hourly load forecasting using time series modeling with peak load estimation capability [J]. IEEE Transactions on Power Systems, 2001, 16(4): 798-805.
[4] Ma Kunlong. Short term distributed load forecasting method based on big data [D]. Changsha: Hunan University, 2014.
[5] Shi Biao, Li Yu Xia, Yu Xhua, Yan Wang. Short-term load forecasting based on modified particle swarm optimizer and fuzzy neural network model [J]. Systems Engineering-Theory and Practice, 2010, 30(1): 158-160.
[6] Wu Jingsong, Geng Zhenduo. Simulation of Robot Obstacle Avoidance Using Improved BP-PID Control [J]. Chinese Journal of Construction Machinery, 2019, 22(04):437-441.
[7] Shi Youheng, Zhang Shuhui, Liu Xiaojie, et al. Blast furnace pressure difference prediction based on XGBoost-BP fusion model optimized by SSA [J]. Journal of Iron and Steel Research, 2019, 36(08):1019-1033.
[8] Li Q W, Yu C M, Yan G X. A new multipredictorensemble decision framework based on deep reinforcementlearning for regional GDP prediction[J]. IEEE Access, 2022, 10: 45266-45279.
[9] TKACZ G. Neural network forecasting of Canadian GD Pgrowth [J]. International Journal of Forecasting, 2001, 17(1):57-69.
[10] Sun Tong, Xu Bin, Jia Hang. Prediction of purchase volume of cross-border e-commerce platform based on Bayes-BP algorithm[J].Computer Applications and Software,2021,38(12):91-96.