摘要
本文针对数学建模竞赛中基于数据驱动的预测问题,详细介绍了数据拟合法、插值法、回归法、神经网络模型、时间序列模型的优缺点,并分别采用这些方法对同一数据集进行了未来一年销售数据的预测。发现对于本文给定的数据,时间序列ARIMA模型预测效果最好。
Regarding to the problem of data-driven prediction in mathematical modeling competition, this paper introduces the advantages and disadvantages of methods such as curve fitting, interpolation, regression, neural network model, and time series model in detail. After that, this paper uses these methods to forecast the sales in the next year on the basis of the same data set. It is found that the ARIMA model of time series reaches the optimal prediction.
出处
《建模与仿真》
2022年第6期1539-1545,共7页
Modeling and Simulation
