检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:唐海波[1] 李睿智 TANG Haibo;LI Ruizhi(School of Business,Shanghai Dianji University,Shanghai 201306,China)
出 处:《上海电机学院学报》2024年第6期367-372,共6页Journal of Shanghai Dianji University
摘 要:中国出口贸易结构正在发生剧烈变化,电子产品所占份额逐年攀升,其中手机产品在电子产品出口份额中的比重较大。为了准确地预测手机出口额,基于SVR模型提出了一种对中国手机出口额的预测方法。首先,选取自2012年以来中国手机月度出口额及影响因素数据;其次,对数据进行预处理以提升预测的准确程度;然后,运用贝叶斯优化方法选取合适参数;最后,选取高斯径向基核函数,通过比较自回归积分滑动平均模型、支持向量回归模型与基于贝叶斯优化的支持向量回归模型,选取最佳模型进行手机出口额的预测。通过比较实际值与预测值发现,基于贝叶斯优化支持向量回归模型对中国手机出口额进行预测的效果最优,证实其对中国手机出口额预测的有效性,以此对中国手机厂商提供决策支持。China's export trade structure is undergoing significant changes,with the share of electronic products steadily increasing year by year,and mobile phone products accounting for a large proportion of the electronic product export share.To accurately predict mobile phone export value,a forecasting method based on the Support Vector Regression(SVR)model is proposed.First,monthly data of China's mobile phone export value and its influencing factors since 2012 are selected.Next,data preprocessing is performed to improve the prediction accuracy.Then,Bayesian optimization is applied to select appropriate parameters.Finally,a Gaussian radial basis kernel function is chosen,and the autoregressive integrated moving average(ARIMA)model,SVR model,and Bayesian-optimized SVR model are compared to select the best model for forecasting mobile phone export value.By comparing the actual and predicted values,it is found that the Bayesian-optimized SVR model provides the most accurate prediction of China's mobile phone export value,confirming its effectiveness in forecasting,and offering decision-making support for Chinese mobile phone manufacturers.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.63