嵌入互联网舆情强度的人民币汇率预测

doi:10.11772/j.issn.1001-9081.2019040726

计算机应用 ›› 2019, Vol. 39 ›› Issue (11): 3403-3408.DOI: 10.11772/j.issn.1001-9081.2019040726

• 应用前沿、交叉与综合 • 上一篇下一篇

嵌入互联网舆情强度的人民币汇率预测

王吉祥¹, 过弋^1,2,3, 戚天梅¹, 王志宏¹, 李真⁴, 汤敏伟⁴

1. 华东理工大学信息科学与工程学院, 上海 200237;
2. 大数据流通与交易技术国家工程实验室, 上海 200237;
3. 上海大数据与互联网受众工程技术研究中心, 上海 200072;
4. 天翼电子商务有限公司风险管理部, 上海 200085

收稿日期:2019-04-28 修回日期:2019-07-09 发布日期:2019-08-26 出版日期:2019-11-10
通讯作者: 过弋
作者简介:王吉祥(1995-),女,浙江温州人,硕士研究生,CCF学生会员,主要研究方向:自然语言处理、数据挖掘;过弋(1975-),男,江苏无锡人,教授,博士,主要研究方向:文本挖掘、知识发现;戚天梅(1994-),女,安徽滁州人,硕士研究生,主要研究方向:自然语言处理、数据挖掘;王志宏(1990-),男,江苏泰兴人,博士研究生,主要研究方向:自然语言处理、文本挖掘;李真(1976-),女,陕西西安人,博士,主要研究方向:金融风险管理、欺诈风险防范;汤敏伟(1990-),男,江苏无锡人,硕士,主要研究方向:异常事件检测、恶意群体识别。
基金资助:
国家重点研发计划项目（2018YFC0807105）；国家自然科学基金资助项目（61462073）；上海市科学技术委员会科研计划项目（17DZ1101003，18511106602，18DZ2252300）。

RMB exchange rate forecast embedded with Internet public opinion intensity

WANG Jixiang¹, GUO Yi^1,2,3, QI Tianmei¹, WANG Zhihong¹, LI Zhen⁴, TANG Minwei⁴

1. School of Information Science and Engineering, East University of Science and Technology, Shanghai 200237, China;
2. National Engineering Laboratory for Big Data Distribution and Exchange Technologies, Shanghai 200237, China;
3. Shanghai Engineering Research Center of Big Data and Internet Audience, Shanghai 200072, China;
4. Department of Risk Management, China Telecom BestPay Company Limited, Shanghai 200085, China

Received:2019-04-28 Revised:2019-07-09 Online:2019-08-26 Published:2019-11-10
Supported by:
This work is partially supported by the National Key Research and Development Program of China (2018YFC0807105), the National Natural Science Foundation of China (61462073), the Scientific Research Project of Science and Technology Committee of Shanghai Municipality (17DZ1101003, 18511106602, 18DZ2252300).

摘要/Abstract

摘要： 针对目前人民币汇率预测研究存在的数据源单一导致难以提升预测效果的问题，提出一种嵌入互联网舆情强度的预测技术，通过融合多方面数据源进行对比分析，有效降低了人民币汇率的预测误差。首先，融合互联网外汇新闻数据和历史行情数据，并将多源文本数据转化为可计算的特征向量；其次，通过情感特征向量构建五种特征组合并对其进行对比，给出了嵌入互联网舆情强度的特征组合作为预测模型输入；最后，设计外汇舆情影响汇率预测的滑动时间窗口，建立基于机器学习的汇率预测模型。实验结果表明，嵌入互联网舆情的特征组合相对于不含舆情的特征组合在均方根误差（RMSE）和平均绝对误差（MAE）上分别提升了9.8%和16.2%；此外，长短期记忆网络（LSTM）预测模型比支持向量回归（SVR）、决策回归（DT）和深度神经网络（DNN）预测模型表现更好。

关键词: 机器学习, 文本向量化, 舆情影响力, 汇率预测, 滑动时间窗口

Abstract: Aiming at the low prediction effect caused by single data source in the current RMB exchange rate forecast research, a forecast technology based on Internet public opinion intensity was proposed. By comparing and analyzing various data sources, the forecast error of RMB exchange rate was effectively reduced. Firstly, the Internet foreign exchange news data and historical market data were fused, and the multi-source text data were converted into the computable vectors. Secondly, five feature combinations based on sentiment feature vectors were constructed and compared, and the feature combination embedded with intensity of Internet public opinion was given as the input of forecast models. Finally, a temporal sliding window of foreign exchange public opinion data was designed, and an exchange rate forecast model based on machine learning was built. Experimental results show that feature combination embedded with Internet public opinion outperforms the feature combination without public opinion by 9.8% and 16.2% in Root Mean Squared Error (RMSE) and Mean Squared Error (MAE). At the same time, the forecast model based on Long Short-Term Memory network (LSTM) is better than that based on Support Vector Regression (SVR), Decision Tree regression (DT) and Deep Neural Network (DNN).

Key words: machine learning, text embedding, public opinion impact, exchange rate forecast, temporal sliding window

中图分类号:

TP391

王吉祥, 过弋, 戚天梅, 王志宏, 李真, 汤敏伟. 嵌入互联网舆情强度的人民币汇率预测[J]. 计算机应用, 2019, 39(11): 3403-3408.

WANG Jixiang, GUO Yi, QI Tianmei, WANG Zhihong, LI Zhen, TANG Minwei. RMB exchange rate forecast embedded with Internet public opinion intensity[J]. Journal of Computer Applications, 2019, 39(11): 3403-3408.

参考文献

[1] 秦喜文,张瑜,董小刚,等. 基于EEMD和SVR的人民币汇率预测[J].东北师大学报(自然科学版), 2017, 49(2):47-51. (QIN X W, ZHANG Y, DONG X G, et al. Forecasting RMB exchange rate based on EEMD and SVR[J]. Journal of Northeast Normal University (Natural Science Edition), 2017, 49(2):47-51.)
[2] 马超. 人民币汇率预测[D]. 济南:山东大学, 2017:8-56. (MA C. RMB exchange rate forecast[D]. Jinan:Shandong University, 2017:8-56.)
[3] FÖRSCHLER F, ALFANO S. Reading between the lines:The effect of language sentiment on economic indicators[C]//Proceedings of the 2017 Enterprise Applications, Markets and Services in the Finance Industry, LNBIP 276. Berlin:Springer, 2017:89-104.
[4] 赵岩,王利明,杨菁. 公共危机事件网络舆情生命周期特征分析及对策研究[J]. 经济研究参考, 2015(16):57-69. (ZHAO Y, WANG L M, YANG J. Analysis of the characteristics of public opinion cycle of public crisis events and its countermeasures[J]. Economic Research Reference, 2015(16):57-69.)
[5] 丁洁. 基于社会网络的网络舆情演化研究[D]. 南京:南京理工大学, 2015:38-44. (DING J. Analysis on the evolution of online public opinion based on social network[D]. Nanjing:Nanjing University of Science and Technology, 2015:38-44.)
[6] PAGOLU V S, REDDY K N, PANDA G, et al. Sentiment analysis of Twitter data for predicting stock market movements[C]//Proceedings of the 2016 International Conference on Signal Processing, Communication, Power and Embedded System. Piscataway:IEEE, 2016:1345-1350.
[7] 陈云松,严飞. 网络舆情是否影响股市行情?基于新浪微博大数据的ARDL模型边限分析[J]. 社会, 2017, 37(2):51-73. (CHEN Y S, YAN F. Does online sentiment predict stock market indices? The ARDL bounds tests based on Sina-microblog data[J]. Society, 2017, 37(2):51-73.)
[8] 张信东,原东良. 基于微博的投资者情绪对股票市场影响研究[J]. 情报杂志, 2017, 36(8):81-87. (ZHANG X D, YUAN D L. Research on the impact of investor sentiment on stock market based on micro-blog[J]. Journal of Intelligence, 2017, 36(8):81-87.)
[9] 朱昶胜,孙欣,冯文芳. 基于R语言的网络舆情对股市影响研究[J]. 兰州理工大学学报, 2018, 44(4):103-108. (ZHU C S, SUN X, FENG W F. Study on the impact of network public opinion on the stock market based on R-language[J]. Journal of Lanzhou University of Technology, 2018, 44(4):103-108.)
[10] LI Q, WANG J, WANG F, et al. The role of social sentiment in stock markets:a view from joint effects of multiple information sources[J]. Multimedia Tools and Applications, 2017, 76(10):12315-12345.
[11] THU T N T, XUAN V D. Using support vector machine in FoRex predicting[C]//Proceedings of the 2018 IEEE International Conference on Innovative Research and Development. Piscataway:IEEE, 2018:1-5.
[12] SEE-TO E W K, YANG Y. Market sentiment dispersion and its effects on stock return and volatility[J]. Electronic Markets, 2017, 27(3):283-296.
[13] 邓景炜. 基于神经网络的外汇汇率预测研究[D]. 广东:暨南大学, 2017:56-65. (DENG J W. Research on foreign exchange rate forecast based on neural network[D]. Guangdong:Jinan University, 2017:56-65.)
[14] LIU C, HOU W, LIU D. Foreign exchange rates forecasting with convolutional neural network[J]. Neural Processing Letters, 2017, 46(3):1095-1119.
[15] CHEN W, ZHANG Y, YEO C K, et al. Stock market prediction using neural network through news on online social networks[C]//Proceedings of the 2017 International Smart Cities Conference. Piscataway:IEEE, 2017:1-6.
[16] LIU Y, QIN Z, LI P, et al. Stock volatility prediction using recurrent neural networks with sentiment analysis[C]//Proceedings of the 2017 International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, LNCS 10350. Berlin:Springer, 2017:192-201.
[17] AWAD M, KHANNA R. Support vector regression[J]. Neural Information Processing Letters and Reviews, 2007, 11(10):203-224.
[18] QUINLAN J R. Induction on decision tree[J]. Machine Learning, 1986, 1(1):81-106.
[19] SCHMIDHUBER J. Deep learning in neural networks:an overview[J]. Neural Networks, 2015, 61:85-117.
[20] SHI X, CHEN Z, WANG H, et al. Convolutional LSTM network:a machine learning approach for precipitation nowcasting[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems. Cambridge, MA:MIT Press, 2015:802-810.
[21] PEDREGOSA F, VAROQUAUX G, GRAMFORT A. Scikit-learn:machine learning in Python[J]. Journal of Machine Learning Research, 2011, 12:2825-2830.
[22] 王嵘冰,徐红艳,李波,等. BP神经网络隐含层节点数确定方法研究[J]. 计算机技术与发展, 2018, 28(4):31-35. (WANG R B, XU H Y, LI B, et al. Research on the method of determining hidden layer nodes in BP neural network[J]. Computer Technology and Development, 2018, 28(4):31-35.)

嵌入互联网舆情强度的人民币汇率预测

RMB exchange rate forecast embedded with Internet public opinion intensity

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	郭棉, 张锦友. 移动边缘计算环境中面向机器学习的计算迁移策略[J]. 计算机应用, 2021, 41(9): 2639-2645.
[2]	毛铭泽, 曹芮浩, 闫春钢. 基于权值多样性的半监督分类算法[J]. 计算机应用, 2021, 41(9): 2473-2480.
[3]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[4]	秦静, 左长青, 汪祖民, 季长清, 王宝凤. 基于堆叠分类器的心电异常监测模型设计[J]. 计算机应用, 2021, 41(3): 887-890.
[5]	姜倩玉, 王凤英, 贾立鹏. 基于感知哈希算法和特征融合的恶意代码检测方法[J]. 计算机应用, 2021, 41(3): 780-785.
[6]	孟祥瑞, 杨文忠, 王婷. 基于图文融合的情感分析研究综述[J]. 计算机应用, 2021, 41(2): 307-317.
[7]	楼豪杰, 郑元林, 廖开阳, 雷浩, 李佳. 基于Siamese-YOLOv4的印刷品缺陷目标检测[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3206-3212.
[8]	刘晓龙, 王士同. 渐进式分离的开放集模糊域自适应算法[J]. 《计算机应用》唯一官方网站, 2021, 41(11): 3127-3131.
[9]	王雅辉, 钱宇华, 刘郭庆. 基于模糊优势互补互信息的有序决策树算法[J]. 计算机应用, 2021, 41(10): 2785-2792.
[10]	蒋阳升, 王胜男, 涂家祺, 李莎, 王红军. 面向高铁站的热舒适度和能耗综合预测[J]. 计算机应用, 2021, 41(1): 249-257.
[11]	朱琳, 于海涛, 雷新宇, 刘静, 王若凡. 基于MRI图像的阿尔茨海默症患者脑网络特征识别算法[J]. 计算机应用, 2020, 40(8): 2455-2459.
[12]	梁登高, 周安民, 郑荣锋, 刘亮, 丁建伟. 基于大小突发块划分的微信支付行为识别模型[J]. 计算机应用, 2020, 40(7): 1970-1976.
[13]	徐周波, 杨健, 刘华东, 黄文文. 基于XGBoost与拓扑结构信息的蛋白质复合物识别算法[J]. 计算机应用, 2020, 40(5): 1510-1514.
[14]	张俊升, 徐晶晶, 余伟. 面部美化图像质量无参考评价方法[J]. 计算机应用, 2020, 40(4): 1184-1190.
[15]	王杨, 赵红东. 基于改进粒子群优化的支持向量机与情景感知的人体活动识别[J]. 计算机应用, 2020, 40(3): 665-671.