基于BP神经网络的数据挖掘方法在需求预测中的应用研究

发布时间：2019-04-24 17:32

【摘要】：【目的/意义】数据挖掘是从庞大数据中挖掘出有潜在价值信息的信息处理技术,它包括神经网络、遗传算法、粗糙集、支持向量机和决策树等多门技术,其中神经网络法具有良好的自学习和含联想储存功能,能够高速寻找优化解,有效提高需求预测准确率。【方法/过程】本文利用BP神经网络具有的优异非线性逼近能力,以我国天然气需求量预测为例,对需求量数据进行训练并采用L-M算法进行改进,最终提高对天然气需求量的预测精度。【结果/结论】实验结果证明,利用数据挖掘中的BP神经网络非线性预测优势能准确捕捉天然气需求预测的变化趋势,为精准预测需求提供了一种有效的工具。
[Abstract]:[objective] data mining is a kind of information processing technology which can mine potential value information from huge data. It includes neural network, genetic algorithm, rough set, support vector machine and decision tree, and other multi-gate technologies, such as neural network, genetic algorithm, rough set, support vector machine, decision tree and so on. The neural network method has good self-learning and associative storage function, can find the optimal solution at high speed, and improve the accuracy of demand prediction effectively. [methods / processes] this paper uses the excellent nonlinear approximation ability of BP neural network, Taking the prediction of natural gas demand in China as an example, this paper trains the demand data and improves the prediction precision of natural gas demand by using L\ {m\} M algorithm. [results / conclusion] the experimental results prove that the prediction precision of natural gas demand is improved. The advantage of nonlinear prediction of BP neural network in data mining can accurately capture the trend of natural gas demand prediction, which provides an effective tool for accurate prediction of natural gas demand.
【作者单位】：西南石油大学经济管理学院;西南油气田公司天然气经济研究所;西南油气田公司重庆气矿;西南油气田公司社会保险中心;
【基金】：国家科技重大专项(2016ZX05062)
【分类号】：F426.22;TP183;TP311.13

【相似文献】