基于BP神经网络在基本药物采购量短期预测中的研究

Short-term prediction of the procurement amount of essential drugs based on the BP neural network

将采购决策行为的具体表现定义为采购量的多少。根据2011年5月-2012年11月湖北省基本药物采购平台的抗生素类部分基本药物品种采购量数据,建立神经网络预测模型,采用BP神经网络来训练建立的模型,并将预测值与实际值相比较。预测值和实际值误差在可接受范围内,研究结果符合预期,预测模型的建立在对基本药物采购量预测方面具有理论意义和应用价值。

ABSTRACT The procurement decision-making behavior is defined as the amount of procurement. According to the procurement data of essential drugs with partial antibiotics stored in the essential drugs procurement platform from May 2011 to November 2012 in Hubei province, a neural network forecast model was established, which was trained using the BP neural network, and the predicted value was compared with the actual value. The error between the predicted value and the actual value was in an acceptable range. So the research results were in line with expectation. The model has both theoretical significance and valuable application in the prediction of the procurement amount of essential drugs. KEY WORDS essential drugs; procurement; BP neural network