基于民航团队旅客销售的预测方法分析

利用Matlab分别用后退的回归分析算法、BP神经网络算法、支持向量机算法和组合预测算法对民航团队销售数据进行预测和比较分析,为民航销售人员提供更加精准的预测信息,从而获得更高的航线收益.分析结果显示:后退的回归分析算法比常用的多元线性回归精准性提高,但是数据结果并不具有可靠性.神经网络算法、支持向量机算法和组合算法比常用的回归分析算法预测的精准度有了明显的提高.支持向量机算法预测精度相对神经网络算法稍低,但是却拥有更强的泛化能力.组合预测算法能避免单一预测方法的误差,更加适合航线销售人员的实际操作.

Analysis on Forecasting Method of Passenger Sales in Civil Aviation

The BP neural network algorithm,the support vector machine algorithm and the combination forecasting algorithm are used to predict and compare the sales data of the civil aviation team by using the regression algorithm.This article provides more accurate forecasting information for civil aviation sales people,resulting in higher route gains.The results of the analysis show that the regression algorithm is more accurate than the commonly used multiple linear regression,but the data is not reliable.Neural networks,support vector machine and combined prediction are often used to improve the predictive accuracy of commonly used regression analysis.Support vector machine prediction accuracy is slightly lower than that of neural network,but it has stronger generalization ability.Combination forecasting can avoid the error of single prediction method,and is more suitable for the actual operation of route sales staff.