基于AR IMA与LOESS的安全生产事故时序预测研究

我国每年安全生产事故都造成大量的人员伤亡和经济损失,因此预防和减少安全生产事故的发生非常重要,利用ARIMA模型和LOESS回归模型组合预测能提高安全生产事故次数预测的精准度.首先建立ARIMA预测模型,用训练集中的预测偏差建立LOESS回归模型,综合两者的预测值,得到最终预测结果.采用2007年9月至2016年7月全国安全生产事故次数数据的实验结果表明:综合2种模型得到的组合预测方法的预测结果精度高于单种模型.

Time Series Prediction of Work Safety Accident Based on ARIMA and LOESS

Work safety accidents of China cause a lot of casualties and economic losses every year, so it is very important to prevent and reduce the occurrence of work safety accidents.Using the combination of ARIMA model and LOESS regression model to forecast the number of work safety accidents is able to improve the accuracy of the prediction.The LOESS regression model is established by the predictiing the deviation of ARIMA model in the training set.The prediction results are obtained by combining the predicted values.The number of national work safety accidents from September 2007 to July 2016 is used as the experiment data.The experimental results show that the accuracy of combination the two models is higher than that of the single model.