|
|
RMB Exchange Rate Forecasting Driven by Cross-Market and Cross-Source Sentiment Analysis |
Cao Wei1,Liao Chenyue1,Zhang Fuwei2() |
1School of Economics, Hefei University of Technology, Hefei 230601, China 2School of Management, Hefei University of Technology, Hefei 230601, China |
|
|
Abstract [Objective] This study aims to introduce cross-market and cross-source sentiment analysis into the RMB exchange rate forecasting model to improve the performance. [Methods] We built a CCSA-DL model for fusing cross-market and cross-source sentiment analysis. First, we used a BERT-TextCNN model to extract deep sentiment features from China and the United States respectively. Then, we shared them with LSTM-based deep features of exchange rate time series to achieve deep fusion, based on which exchange rate forecasting is realized with the help of SVM model. [Results] Compared with the baseline model, the CCSA-DL model achieved optimal performance in predicting indicators and economic returns. Especially compared with the LSTM prediction model, there was an average improvement of about 16.77% in the three evaluation indicators. [Limitations] The source of sentiment analysis data needs to be further expanded and optimized. [Conclusions] The CCSA-DL model with cross-market and cross-source sentiment analysis has better exchange rate forecasting performance and economic returns.
|
Received: 02 November 2022
Published: 12 September 2023
|
|
Fund:National Natural Science Foundation of China(71801072);Hefei University of Technology Project for Young Teachers’ Research and Innovation,the Fundamental Research Funds for the Central Universities(JZ2020HGQA0181) |
Corresponding Authors:
Zhang Fuwei,ORCID:0009-0002-6193-6669,E-mail:zhfuwei@126.com。
|
[1] |
何光辉, 杨何灿. 中国境内人民币汇率弹性及其市场机制研究[J]. 数量经济技术经济研究, 2022, 39(12): 46-68.
|
[1] |
(He Guanghui, Yang Hecan. The RMB Exchange-Rate Flexibility and Market Mechanisms in China[J]. Journal of Quantitative & Technological Economics, 2022, 39(12): 46-68.)
|
[2] |
王盼盼. 中美贸易摩擦、美国经济政策不确定性与人民币汇率波动[J]. 世界经济研究, 2021(7): 75-92.
|
[2] |
(Wang Panpan. Sino-U.S.Trade Frictions,U.S. Economic Policy Uncertainty and RMB Exchange Rate Fluctuations[J]. World Economy Studies, 2021(7): 75-92.)
|
[3] |
Wada T. Out-of-Sample Forecasting of Foreign Exchange Rates: The Band Spectral Regression and LASSO[J]. Journal of International Money and Finance, 2022, 128: 102719.
doi: 10.1016/j.jimonfin.2022.102719
|
[4] |
Hu M Y, Tsoukalas C. Combining Conditional Volatility Forecasts Using Neural Networks: An Application to the EMS Exchange Rates[J]. Journal of International Financial Markets, Institutions and Money, 1999, 9(4): 407-422.
doi: 10.1016/S1042-4431(99)00015-3
|
[5] |
Yao J T, Tan C L. A Case Study on Using Neural Networks to Perform Technical Forecasting of Forex[J]. Neurocomputing, 2000, 34(1-4): 79-98.
doi: 10.1016/S0925-2312(00)00300-3
|
[6] |
王相宁, 杨杰. 基于SSA-ARIMA-HPSO-SVM组合模型的汇率预测[J]. 统计与决策, 2020, 36(23): 134-138.
|
[6] |
(Wang Xiangning, Yang Jie. Exchange Rate Forecast Based on SSA-ARIMA-HPSO-SVM Combined Model[J]. Statistics & Decision, 2020, 36(23): 134-138.)
|
[7] |
张蕾, 孙尚红, 王月. 基于深度学习LSTM模型的汇率预测[J]. 统计与决策, 2021, 37(13): 158-162.
|
[7] |
(Zhang Lei, Sun Shanghong, Wang Yue. Exchange Rate Forecast Based on LSTM Model of Deep Learning[J]. Statistics & Decision, 2021, 37(13): 158-162.)
|
[8] |
任仙玲, 邓磊. 网络舆情对人民币汇率的冲击效应——基于中美贸易摩擦事件[J]. 管理科学, 2019, 32(6): 46-56.
|
[8] |
(Ren Xianling, Deng Lei. Effect of Network Public Opinion Shocks on Exchange Rate: Evidence from the China-US Trade Friction[J]. Journal of Management Science, 2019, 32(6): 46-56.)
|
[9] |
王轩, 杨海珍. 基于互联网搜索指数的多因素集成下人民币汇率预测[J]. 系统工程学报, 2017, 32(3): 360-369.
|
[9] |
(Wang Xuan, Yang Haizhen. Research on the Forecasting of RMB Exchange Rate Based on Multi Factor Integration and Web-Searching Index[J]. Journal of Systems Engineering, 2017, 32(3): 360-369.)
|
[10] |
王吉祥, 过弋, 戚天梅, 等. 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.
doi: 10.11772/j.issn.1001-9081.2019040726
|
[10] |
(Wang Jixiang, Guo Yi, Qi Tianmei, et al. RMB Exchange Rate Forecast Embedded with Internet Public Opinion Intensity[J]. Journal of Computer Applications, 2019, 39(11): 3403-3408.)
doi: 10.11772/j.issn.1001-9081.2019040726
|
[11] |
汪文隽, 王亦天, 操玮, 等. 基于多模态投资者情绪数据的USD/CNY汇率波动率预测研究[J]. 计算机应用研究, 2020, 37(S2): 152-155.
|
[11] |
(Wang Wenjun, Wang Yitian, Cao Wei, et al. Forecasting Volatility of USD/CNY Exchange Rate Based on Multimode Investor Sentiment Data[J]. Application Research of Computers, 2020, 37(S2): 152-155.)
|
[12] |
Pang B, Lee L. Opinion Mining and Sentiment Analysis[J]. Foundations and Trends in Information Retrieval, 2008, 2(1-2): 1-135.
doi: 10.1561/1500000011
|
[13] |
蒋翠清, 梁坤, 丁勇, 等. 基于社会媒体的股票行为预测[J]. 中国管理科学, 2015, 23(1): 17-24.
|
[13] |
(Jiang Cuiqing, Liang Kun, Ding Yong, et al. Predicting Stock Behaviorvia Social Media[J]. Chinese Journal of Management Science, 2015, 23(1): 17-24.)
|
[14] |
崔炎炎, 刘立新. 网络舆情赋能金融科技股票收盘价预测研究[J]. 统计研究, 2022, 39(6): 148-160.
|
[14] |
(Cui Yanyan, Liu Lixin. Research on the Impact of Internet Public Opinion on Fintech Stock Closing Price Forecast[J]. Statistical Research, 2022, 39(6): 148-160.)
|
[15] |
Ho K Y, Shi Y L, Zhang Z Y. Does News Matter in China’s Foreign Exchange Market? Chinese RMB Volatility and Public Information Arrivals[J]. International Review of Economics & Finance, 2017, 52: 302-321.
|
[16] |
Chang M J, Matsuki T. Exchange Rate Forecasting with Real-Time Data: Evidence from Western Offshoots[J]. Research in International Business and Finance, 2022, 59: 101538.
doi: 10.1016/j.ribaf.2021.101538
|
[17] |
杨长江, 钟宁桦. 购买力平价与人民币均衡汇率[J]. 金融研究, 2012(1): 36-50.
|
[17] |
(Yang Changjiang, Zhong Ninghua. Purchasing Power Parity and Equilibrium Exchange Rate of RMB[J]. Journal of Financial Research, 2012(1): 36-50.)
|
[18] |
张伟伟, 苗思雨. 美元利率汇率波动对中国经济的影响——基于美元与人民币利率汇率联动关系的实证检验[J]. 当代经济研究, 2020(8): 101-112.
|
[18] |
(Zhang Weiwei, Miao Siyu. The Impact of US Dollar Interest Rate and Exchange Rate Fluctuations on China’s Economy—Based on the Empirical Test of the Linkage Relations Between USD and CNY Interest Rates and Exchange Rates[J]. Contemporary Economic Research, 2020(8): 101-112.)
|
[19] |
齐晓楠, 成思危, 汪寿阳, 等. 美联储量化宽松政策对中国经济和人民币汇率的影响[J]. 管理评论, 2013, 25(5): 3-10.
|
[19] |
(Qi Xiaonan, Cheng Siwei, Wang Shouyang, et al. The Influence of the Second Round of Quantitative Easing Policy of the United States on RMB Exchange Rate[J]. Management Review, 2013, 25(5): 3-10.)
|
[20] |
Kempa B, Wilde W. Sources of Exchange Rate Fluctuations with Taylor Rule Fundamentals[J]. Economic Modelling, 2011, 28(6): 2622-2627.
doi: 10.1016/j.econmod.2011.08.004
|
[21] |
MacDonald R, Clark P B, Org R, et al. Exchange Rates and Economic Fundamentals: A Methodological Comparison of Beers and Feers[A]// Recent Economic Thought Series[M]. Springer, 1998.
|
[22] |
潘锡泉. 中美利率和汇率动态效应研究: 理论与实证——基于拓展的非抛补利率平价模型的研究[J]. 国际贸易问题, 2013(6): 76-87.
|
[22] |
(Pan Xiquan. Research on Dynamic Effects of China-U.S. Interest Rate and Exchange Rate: A Theoretical and Empirical Analysis Based on Extended Uncovered Interest-Rate Parity Model[J]. Journal of International Trade, 2013(6): 76-87.)
|
[23] |
李欣珏. 及时性自适应高维经济基本面建模与汇率预测分析[J]. 系统工程理论与实践, 2020, 40(6): 1478-1494.
doi: 10.12011/1000-6788-2020-0466-17
|
[23] |
(Li Xinjue. The Real Time Adaptive High Dimensional Economic Basics Modeling with Application in Exchange Rate Forecasting[J]. Systems Engineering-Theory & Practice, 2020, 40(6): 1478-1494.)
doi: 10.12011/1000-6788-2020-0466-17
|
[24] |
徐梅, 梅世强, 李菊栋. 经济波动随机时间序列模型的比较研究[J]. 预测, 2001, 20(6): 56-60.
|
[24] |
(Xu Mei, Mei Shiqiang, Li Judong. Study on Stochastic Time Series Models of Business Fluctuation[J]. Rorecasting, 2001, 20(6): 56-60.)
|
[25] |
林志华, 郭正光, 陈镇坤. 基于随机搜索变量方法的经济预警指数自回归预测模型[J]. 统计与决策, 2015(8): 34-36.
|
[25] |
(Lin Zhihua, Guo Zhengguang, Chen Zhenkun. Autoregressive Prediction Model of Economic Early Warning Index Based on Random Search Variable Method[J]. Statistics & Decision, 2015(8): 34-36.)
|
[26] |
吴丽萍, 陈宝峰, 张旺. “十二五”时期中国水利投资预测研究[J]. 经济与管理, 2011, 25(8): 5-10.
|
[26] |
(Wu Liping, Chen Baofeng, Zhang Wang. Forecast on Water Conservancy Investment in China in “The Twelfth Five” Period[J]. Economy and Management, 2011, 25(8): 5-10.)
|
[27] |
石炀. 股票价格与人民币汇率的联动性分析——基于Copula-ARIMA模型[J]. 山西财经大学学报, 2019, 41(S2): 14-19.
|
[27] |
(Shi Yang. Linkage Analysis of Stock Price and RMB Exchange Rate—Based on Copula-ARIMA Model[J]. Journal of Shanxi University of Finance and Economics, 2019, 41(S2): 14-19.)
|
[28] |
崔峰, 韩传峰, 刘兴华, 等. 基于小波GARCH模型的协整策略交易信号指标体系优化[J]. 中国管理科学, 2023, 31(2): 129-137.
|
[28] |
(Cui Feng, Han Chuanfeng, Liu Xinghua, et al. Trading Signal Index Optimization of Co-Integration Strategy Based on Wavelet GARCH Model[J]. Chinese Journal of Management Science, 2023, 31(2): 129-137.)
|
[29] |
Refenes A N, Zapranis A, Francis G. Stock Performance Modeling Using Neural Networks: A Comparative Study with Regression Models[J]. Neural Networks, 1994, 7(2): 375-388.
doi: 10.1016/0893-6080(94)90030-2
|
[30] |
惠晓峰, 胡运权, 胡伟. 基于遗传算法的BP神经网络在汇率预测中的应用研究[J]. 数量经济技术经济研究, 2002, 19(2): 80-83.
|
[30] |
(Hui Xiaofeng, Hu Yunquan, Hu Wei. Research on the Application of BP Neural Network Based on Genetic Algorithm in Exchange Rate Forecasting[J]. Quantitative & Technical Economics, 2002, 19(2): 80-83.)
|
[31] |
Fu S B, Li Y W, Sun S L, et al. Evolutionary Support Vector Machine for RMB Exchange Rate Forecasting[J]. Physica A: Statistical Mechanics and Its Applications, 2019, 521: 692-704.
doi: 10.1016/j.physa.2019.01.026
|
[32] |
Qiu J Y, Wang B, Zhou C J. Forecasting Stock Prices with Long-Short Term Memory Neural Network Based on Attention Mechanism[J]. PLoS One, 2020, 15(1): e0227222.
doi: 10.1371/journal.pone.0227222
|
[33] |
熊志斌. 基于CEEMDAN与LSTM的人民币汇率分析与预测[J]. 数理统计与管理, 2022, 41(3): 507-525.
|
[33] |
(Xiong Zhibin. RMB Exchange Rate Analysis and Its Forecasting Based on CEEMDAN and LSTM[J]. Journal of Applied Statistics and Management, 2022, 41(3): 507-525.)
|
[34] |
Nassirtoussi A K, Aghabozorgi S, Wah T Y, et al. Text Mining of News-Headlines for FOREX Market Prediction: A Multi-layer Dimension Reduction Algorithm with Semantics and Sentiment[J]. Expert Systems with Applications, 2015, 42(1): 306-324.
doi: 10.1016/j.eswa.2014.08.004
|
[35] |
张杰, 张永卿, 翟东升. 融合财经新闻信息的汇率波动预测[J]. 系统工程, 2021, 39(3): 121-131.
|
[35] |
(Zhang Jie, Zhang Yongqing, Zhai Dongsheng. The Prediction of Exchange Rate Fluctuation Based on Financial News Information[J]. Systems Engineering, 2021, 39(3): 121-131.)
|
[36] |
Lin Y, Wang R Y, Gong X Y, et al. Cross-Correlation and Forecast Impact of Public Attention on USD/CNY Exchange Rate: Evidence from Baidu Index[J]. Physica A: Statistical Mechanics and Its Applications, 2022, 604: 127686.
doi: 10.1016/j.physa.2022.127686
|
[37] |
杨超, 姜昊, 雷峥嵘. 基于文本挖掘和百度指数的汇率预测[J]. 统计与决策, 2019, 35(13): 85-87.
|
[37] |
(Yang Chao, Jiang Hao, Lei Zhengrong. Exchange Rate Forecast Based on Text Mining and Baidu Index[J]. Statistics & Decision, 2019, 35(13): 85-87.)
|
[38] |
范昊, 何灏. 融合上下文特征和BERT词嵌入的新闻标题分类研究[J]. 情报科学, 2022, 40(6): 90-97.
|
[38] |
(Fan Hao, He Hao. News Title Classification Based on Contextual Features and BERT Word Embedding[J]. Information Science, 2022, 40(6): 90-97.)
|
[39] |
Devlin J, Chang M W, Lee K, et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding[OL]. arXiv Preprint, arXiv:1810.04805.
|
[40] |
Kim Y. Convolutional Neural Networks for Sentence Classification[OL]. arXiv Preprint, arXiv:1408.5882.
|
[41] |
Hochreiter S, Schmidhuber J. Long Short-Term Memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
doi: 10.1162/neco.1997.9.8.1735
pmid: 9377276
|
[42] |
Jia D, Li Z Y, Zhang C W. Detection of Cervical Cancer Cells Based on Strong Feature CNN-SVM Network[J]. Neurocomputing, 2020, 411: 112-127.
doi: 10.1016/j.neucom.2020.06.006
|
[43] |
姚宏亮, 徐礼维, 杨静, 等. 基于动态影响图的股市趋势预测[J]. 计算机工程与应用, 2022, 58(15): 162-168.
doi: 10.3778/j.issn.1002-8331.2101-0050
|
[43] |
(Yao Hongliang, Xu Liwei, Yang Jing, et al. Stock Market Trend Prediction Based on Dynamic Influence Diagrams[J]. Computer Engineering and Applications, 2022, 58(15): 162-168.)
doi: 10.3778/j.issn.1002-8331.2101-0050
|
[44] |
刘玉敏, 李洋, 赵哲耘. 基于特征选择的RF-LSTM模型成分股价格趋势预测[J]. 统计与决策, 2021, 37(1): 157-160.
|
[44] |
(Liu Yumin, Li Yang, Zhao Zheyun. Prediction of Component Price Trend of RF-LSTM Model Based on Feature Selection[J]. Statistics & Decision, 2021, 37(1): 157-160.)
|
[45] |
胡雪梅, 蒋慧凤. 具有技术指标的逻辑回归模型预测谷歌股票的涨跌趋势[J]. 系统科学与数学, 2021, 41(3): 802-823.
|
[45] |
(Hu Xuemei, Jiang Huifeng. Logistic Regression Model with Technical Indicators Predicts Ups and Downs for Google Stock Prices[J]. Journal of Systems Science and Mathematical Sciences, 2021, 41(3): 802-823.)
|
[46] |
张友国, 孙博文, 谢锐. 新冠肺炎疫情的经济影响分解与对策研究[J]. 统计研究, 2021, 38(8): 68-82.
|
[46] |
(Zhang Youguo, Sun Bowen, Xie Rui. Study on Decomposition and Countermeasures of the Economic Impact of Covid-19[J]. Statistical Research, 2021, 38(8): 68-82.)
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|