In recent years, the rapid development of e-commerce has brought great convenience to people. Compared with traditional business environment, e-commerce is more dynamic and complex, which brings many challenges. Data mining technology can help people better deal with these challenges. Traditional data mining technology cannot effectively use the massive data in the electricity supplier, it relies on the time-consuming and labour-consuming characteristic engineering, and the obtained model is not scalable. Convolutional neural network can effectively use a large amount of data, and can automatically extract effective features from the original data, with higher availability. In this paper, convolutional neural network is used to mine e-commerce data to achieve the prediction of commodity sales. First, this article combines the inherent nature of the relevant merchandise information with the original cargo log data that can be converted into a specific “data frame” format. Raw log data includes items sold over a long period of time, price, quantity view, browse, search, search, times collected, number of items added to cart, and many other metrics. Then, convolutional neural network is applied to extract effective features on the data frame. Finally, the final layer of the convolutional neural network uses these features to predict sales of goods. This method can automatically extract effective features from the original structured time series data by convolutional neural network, and further use these features to achieve sales forecast. The validity of the proposed algorithm is verified on the real e-commerce data set.

中文翻译：

---

卷积神经网络及其在电子商务数据挖掘和销售预测中的应用

近年来，电子商务的飞速发展为人们带来了极大的便利。与传统的商业环境相比，电子商务更加动态和复杂，带来了许多挑战。数据挖掘技术可以帮助人们更好地应对这些挑战。传统的数据挖掘技术无法有效地利用电力供应商中的海量数据，它依赖于耗时费力的特性工程，并且所获得的模型不可扩展。卷积神经网络可以有效地使用大量数据，并且可以从原始数据中自动提取有效特征，具有更高的可用性。本文使用卷积神经网络来挖掘电子商务数据，以实现商品销售的预测。第一，本文将相关商品信息的固有性质与可以转换为特定“数据框”格式的原始货物日志数据结合在一起。原始日志数据包括长时间出售的商品，价格，数量视图，浏览，搜索，搜索，收集的时间，添加到购物车的商品数量以及许多其他指标。然后，使用卷积神经网络提取数据帧上的有效特征。最后，卷积神经网络的最后一层使用这些功能来预测商品的销售。该方法可以通过卷积神经网络自动从原始结构化时间序列数据中提取有效特征，并进一步使用这些特征来实现销售预测。在真实的电子商务数据集上验证了所提算法的有效性。