本文已被：浏览 1631次 下载 2583次
Received:October 31, 2017 Revised:November 21, 2017
Received:October 31, 2017 Revised:November 21, 2017
中文摘要: 随着信息技术的不断发展，基于网络数据对事物近期发展态势预测成为热点.本文以北京市月度游客量预测为目标，以相关网络关键词搜索指数为自变量建立了BP神经网络、支持向量回归和随机森林三种单一预测模型，在此基础上构建组合模型以提高预测准确度.实验结果表明：基于GBDT建立的组合模型达到了较高的预测准确度，误差仅为3.16%，预测结果可以为旅游管理部门提供决策支持.
Abstract:With the continuous development of information technology, the forecast of the recent development of things based on the network data has become a hotspot. In order to predict the monthly number of tourists in Beijing, this study established three kinds of single models with the search index of the relevant network keywords as independent variables:BP neural network, support vector regression, and random forest, and constructed a variety of combinatorial models to improve the prediction accuracy. The experimental results show that the combination of models based on GBDT have achieved higher prediction accuracy, the error is 3.16%. The forecast results can provide decision support for tourism management.
keywords: tourists quantity forecasting network search data machine learning algorithm combinatorial model
文章编号： 中图分类号： 文献标志码：
基金项目:陕西省重点学科资助项目（107-00x901）
引用文本：
谢天保,赵萌.基于网络搜索数据的游客量组合预测模型.计算机系统应用,2018,27(7):199-204
XIE Tian-Bao,ZHAO Meng.Multi-Models Combination Tourists Quantity Forecasting Based on Network Search Data.COMPUTER SYSTEMS APPLICATIONS,2018,27(7):199-204
谢天保,赵萌.基于网络搜索数据的游客量组合预测模型.计算机系统应用,2018,27(7):199-204
XIE Tian-Bao,ZHAO Meng.Multi-Models Combination Tourists Quantity Forecasting Based on Network Search Data.COMPUTER SYSTEMS APPLICATIONS,2018,27(7):199-204
