基于优化BP神经网络的销售预测算法研究

Research on Sales Forecasting Based on Improved BP Neural Network

已知国内房屋售价具有一定的不完整的规律性,其会因季节变换、人群流动、国家相关政策等一系列因素而呈现一定的规律。与此同时,该规律性并没有确定的单一因子可以直接影响,故其售价与全部因素之间的关系也是非线性的。针对这一问题,利用神经网络输入量的非线性、冗杂性和可不完整性,对一段时期内的房屋售价进行预测是一种合理的预测方法。基于BP神经网络传输阈值的不确定性,利用时间序列方法对因子数据进行平行预测,再利用遗传算法和BP神经网络对所得结果进行二次优化,以达到接近实际的精准预测的目的。经过使用某房地产企业的历史销售数据进行反复仿真实验,其结果表明所提出的优化算法模型预测精度逼近于实际销售结果,达到了精准预测的目标。

It is known that the price of houses in China has some incomplete regularity,which will show a certain regularity due to a series of factors such as seasonal change,crowd flow,and relevant national policies.At the same time,there is no definite single factor that can directly affect the regularity,so the relationship between the price and all factors is nonlinear.In order to solve this problem,it is a reasonable forecasting method to forecast the house price in a period of time by using the nonlinear,miscellaneous and incomplete input of neural network.Based on the uncertainty of the transmission threshold of BP neural network,the time series method is used to predict the factor data in parallel,and then the genetic algorithm and BP neural network are used to optimize the results for the purpose of accurate prediction.Through repeated simulation experiments with the historical sales data of a real estate enterprise,it is showed that the prediction accuracy of the proposed optimization algorithm model is close to the actual sales results,and achieves the goal of accurate prediction.