School of Physical Education, Henan University of Science and Technology, Luoyang, Henan 471000, China.
Comput Intell Neurosci. 2022 Jul 9;2022:4298235. doi: 10.1155/2022/4298235. eCollection 2022.
Commodity prices play a unique role as a lever to regulate the economy. Price forecasting is an important part of macrodecision-making and micromanagement. Because there are many factors affecting the price of goods, price prediction has become a difficulty in research. According to the characteristics that price data are also affected by other factors except for time series, a multifactor LSTM price prediction method is proposed based on the long-term and short-term memory network (LSTM) deep learning algorithm. This method not only makes use of the memory of LSTM to historical data but also introduces the influence of external factors on price through the full connection layer, which provides a new idea for solving the problem of price prediction. Compared with BP neural network, the experimental results show that this method has higher accuracy and better stability. Analyze the commodity description and commodity price characteristics, find out the commodities similar to the target commodity, complete the commodity price data by using the historical price data of similar commodities, and establish the training set to verify the validity of the proposed method.
商品价格作为调节经济的杠杆具有独特作用。价格预测是宏观决策和微观管理的重要组成部分。由于影响商品价格的因素很多，因此价格预测已成为研究难点。针对商品价格数据除了受时间序列影响外还受到其他因素影响的特点，提出了一种基于长短期记忆网络（LSTM）深度学习算法的多因素 LSTM 价格预测方法。该方法不仅利用 LSTM 的记忆功能对历史数据进行建模，还通过全连接层引入外部因素对价格的影响，为解决价格预测问题提供了新的思路。与 BP 神经网络相比，实验结果表明，该方法具有更高的准确性和更好的稳定性。分析商品描述和商品价格特征，找出与目标商品相似的商品，利用相似商品的历史价格数据完成商品价格数据，并建立训练集，以验证所提出方法的有效性。
