考虑美元人民币汇率影响的企业债收益预测研究——基于LSTM神经网络  

Study on the Prediction of Corporate Bond return considering the effect of US dollar RMB Exchange rate——Based on LSTM neural network

作　　者：周颖 ZHOU Ying(Managament college,Shanghai University of Science and Technology,Shanghai 200093,China)

机构地区：[1]上海理工大学管理学院

出　　处：《经济研究导刊》2019年第17期149-151,154,共4页Economic Research Guide

摘　　要：汇率变动对我国金融市场具有不可忽视的影响力。因此,首先对上证企债指数进行主成分分析,筛选出最具代表性的特征值,根据特征值构建企债收益指标,在考虑美元人民币汇率影响的基础上,建立LSTM的预测模型,研究企债收益的规律,并对未来60个交易日的企债对数指数收益率进行仿真预测。希望研究结果可以为广大企债投资者做投资买卖决策时提供重要的参考依据。The exchange rate change has an important influence on China’s financial market.Therefore,firstly,the principal component analysis of Shanghai enterprise bond index is carried out,and the most representative eigenvalues are screened out. According to the characteristic value,the index of enterprise bond income is constructed.On the basis of considering the influence of US dollar RMB exchange rate,the prediction model of LSTM is established,the law of enterprise bond return is studied,and the rate of return of enterprise bond logarithmic index in the next 60 trading days is simulated and predicted.It is hoped that the research results can provide an important reference for the majority of corporate bond investors to make investment and trading decisions.

关 键 词：收益预测 上证企债指数 汇率 LSTM 

分 类 号：F822[经济管理—财政学] TP21[自动化与计算机技术—检测技术与自动化装置]