Forex(foreign exchange)is a special financial market that entails both high risks and high profit opportunities for traders.It is also a very simple market since traders can profit by just predicting the direction of ...Forex(foreign exchange)is a special financial market that entails both high risks and high profit opportunities for traders.It is also a very simple market since traders can profit by just predicting the direction of the exchange rate between two currencies.However,incorrect predictions in Forex may cause much higher losses than in other typical financial markets.The direction prediction requirement makes the problem quite different from other typical time-series forecasting problems.In this work,we used a popular deep learning tool called“long short-term memory”(LSTM),which has been shown to be very effective in many time-series forecasting problems,to make direction predictions in Forex.We utilized two different data sets—namely,macroeconomic data and technical indicator data—since in the financial world,fundamental and technical analysis are two main techniques,and they use those two data sets,respectively.Our proposed hybrid model,which combines two separate LSTMs corresponding to these two data sets,was found to be quite successful in experiments using real data.展开更多
The article first addresses the following questions:“Why does gross domestic product(GDP)rises,but the stock market value falls?”;“Among the macroeconomic factors,which factor has a greater impact on the promotion ...The article first addresses the following questions:“Why does gross domestic product(GDP)rises,but the stock market value falls?”;“Among the macroeconomic factors,which factor has a greater impact on the promotion of investment value in the securities market?”.With these questions in mind,we put forward a hypothesis emphasizing on the impact of macroeconomic factors on the value of the stock market based on existing research and used the regression method to verify this hypothesis.The following conclusions were drawn:(1)variables that have a positive nonlinear relationship with stock market value include balance of payments surplus,rising GDP level,M1,the whole society’s fixed asset investment,and national per capita disposable income;(2)variables that have a negative nonlinear relationship with stock market value include deposit,loan interest rate,new RMB loan amount,consumer price index(CPI),and producer price index;(3)deposit reserve ratio has an S-shaped curve relationship with stock market value;(4)exchange rate has an inverted U-shaped curve relationship with stock market value.展开更多
Macroeconomic Overview:The U.S.dollar has fallen 4%against a broad collection of widely circulated currencies since January.While the magnitude of the decline may not appear large,it does signal an important reversal ...Macroeconomic Overview:The U.S.dollar has fallen 4%against a broad collection of widely circulated currencies since January.While the magnitude of the decline may not appear large,it does signal an important reversal relative to recent years.Against the same broad collection of currencies,the U.S.dollar had consistently strengthened since 2013。展开更多
The aim of the article is to present non-clasical copyrighted algorithm for prediction of time series, presenting macroeconomic indicators and stock market indices. The algorithm is based on artificial neural networks...The aim of the article is to present non-clasical copyrighted algorithm for prediction of time series, presenting macroeconomic indicators and stock market indices. The algorithm is based on artificial neural networks and multi-resolution analysis （the algorithm is based on Daubechies wavelet）. However, the main feature of the algorithm, which gives a good quality of the forecasts, is all included in the series analysis division into, a few partial under-series and prediction dependence on a number of other economic series. The algorithm used for the prediction, is copyrighted algorithm, labeled M.H-D in this article. Application of the algorithm was performed on a series presenting WIG 20. The forecast of WIG 20 was conditional on trading the Dow Jones, DAX, Nikkei, Hang Seng, taking into account the sliding time window. As an example application of copyrighted model, the forecast of WIG 20 for a period of two years, one year, six month was appointed. An empirical example is described. It shows that the proposed model can predict index with the scale of two years, one year, a half year and other intervals. Precision of prediction is satisfactory. An average absolute percentage error of each forecast was： 0.0099%---for two-year forecasts WIG 20; 0.0552%--for the annual forecast WIG 20; and 0.1788%---for the six-month forecasts WIG 20.展开更多
Official monthly unemployment data is unavailable in China, while intense public interest in unemployment requires timely and accurate information. Using data on web queries from lead search engines in China, Baidu an...Official monthly unemployment data is unavailable in China, while intense public interest in unemployment requires timely and accurate information. Using data on web queries from lead search engines in China, Baidu and Google, I build two indices measuring intensity of online unemployment-related searches. The unemployment-related search indices identify a structural break in the time series between October and November 2008, which corresponds to a turning point indicated by some macroeconomic indicators. The unemployment- related search indices are proven to have significant correlation with Purchasing Managers＇ Employment Indices and a set of macroeconomic indicators that are closely related to changes in unemployment in China. The results of Granger causality analysis show that the unemployment-related search indices can improve predictions of the c indicators. It suggests that unemploy- ment-related searches can potentially provide valuable, timely, and low-cost information for macroeconomic monitoring.展开更多
文摘Forex(foreign exchange)is a special financial market that entails both high risks and high profit opportunities for traders.It is also a very simple market since traders can profit by just predicting the direction of the exchange rate between two currencies.However,incorrect predictions in Forex may cause much higher losses than in other typical financial markets.The direction prediction requirement makes the problem quite different from other typical time-series forecasting problems.In this work,we used a popular deep learning tool called“long short-term memory”(LSTM),which has been shown to be very effective in many time-series forecasting problems,to make direction predictions in Forex.We utilized two different data sets—namely,macroeconomic data and technical indicator data—since in the financial world,fundamental and technical analysis are two main techniques,and they use those two data sets,respectively.Our proposed hybrid model,which combines two separate LSTMs corresponding to these two data sets,was found to be quite successful in experiments using real data.
文摘The article first addresses the following questions:“Why does gross domestic product(GDP)rises,but the stock market value falls?”;“Among the macroeconomic factors,which factor has a greater impact on the promotion of investment value in the securities market?”.With these questions in mind,we put forward a hypothesis emphasizing on the impact of macroeconomic factors on the value of the stock market based on existing research and used the regression method to verify this hypothesis.The following conclusions were drawn:(1)variables that have a positive nonlinear relationship with stock market value include balance of payments surplus,rising GDP level,M1,the whole society’s fixed asset investment,and national per capita disposable income;(2)variables that have a negative nonlinear relationship with stock market value include deposit,loan interest rate,new RMB loan amount,consumer price index(CPI),and producer price index;(3)deposit reserve ratio has an S-shaped curve relationship with stock market value;(4)exchange rate has an inverted U-shaped curve relationship with stock market value.
文摘Macroeconomic Overview:The U.S.dollar has fallen 4%against a broad collection of widely circulated currencies since January.While the magnitude of the decline may not appear large,it does signal an important reversal relative to recent years.Against the same broad collection of currencies,the U.S.dollar had consistently strengthened since 2013。
文摘The aim of the article is to present non-clasical copyrighted algorithm for prediction of time series, presenting macroeconomic indicators and stock market indices. The algorithm is based on artificial neural networks and multi-resolution analysis （the algorithm is based on Daubechies wavelet）. However, the main feature of the algorithm, which gives a good quality of the forecasts, is all included in the series analysis division into, a few partial under-series and prediction dependence on a number of other economic series. The algorithm used for the prediction, is copyrighted algorithm, labeled M.H-D in this article. Application of the algorithm was performed on a series presenting WIG 20. The forecast of WIG 20 was conditional on trading the Dow Jones, DAX, Nikkei, Hang Seng, taking into account the sliding time window. As an example application of copyrighted model, the forecast of WIG 20 for a period of two years, one year, six month was appointed. An empirical example is described. It shows that the proposed model can predict index with the scale of two years, one year, a half year and other intervals. Precision of prediction is satisfactory. An average absolute percentage error of each forecast was： 0.0099%---for two-year forecasts WIG 20; 0.0552%--for the annual forecast WIG 20; and 0.1788%---for the six-month forecasts WIG 20.
基金The Project is sponsored by the Scientific Research Foundation for the Retttmed Overseas Chinese Scholars, Ministry of Education of PRC, and supported by Beijing Natural Science Foundation （No. 9144025）. I would like to thank the reviewers who provide insightful comments and suggestions for improving this paper. I also would like to thank the editors who proofread and edit the paper. Without the supportive work of the reviewers and editors, this paper would not have been possible.
文摘Official monthly unemployment data is unavailable in China, while intense public interest in unemployment requires timely and accurate information. Using data on web queries from lead search engines in China, Baidu and Google, I build two indices measuring intensity of online unemployment-related searches. The unemployment-related search indices identify a structural break in the time series between October and November 2008, which corresponds to a turning point indicated by some macroeconomic indicators. The unemployment- related search indices are proven to have significant correlation with Purchasing Managers＇ Employment Indices and a set of macroeconomic indicators that are closely related to changes in unemployment in China. The results of Granger causality analysis show that the unemployment-related search indices can improve predictions of the c indicators. It suggests that unemploy- ment-related searches can potentially provide valuable, timely, and low-cost information for macroeconomic monitoring.
