| Popis: |
Long term historical records of the stock markets are widely used in technical research to define, understand and analyze stock market's time series trends and patterns which can be used to generate huge profits during trading sessions Even though, technical analysis using different technical measures have been shown to be helpful in forecasting market patterns, formulating specific trading rule is a challenging task In this research paper, we have tried to analyze investor's sentiments considering US presidential elections and effects of Covid 19 as an explicit fluctuating factor affecting stock market performance In addition to this, in this research work,we have tried to identify correct and better trading rules and trading points,technical indicators to be considered using mathematical formulations, to determine when to buy or sell stocks Thus, given dynamically varying stock market behaviour in high frequency trading environment, it is important to integrate market sentiments into forecasting operations This paper combines sentiments into stock forecasting model using the log bilinear (LBL) model for short term stock market's sentiment pattern learning and recurrent neural (RNN) for long term sentiments pattern learning which achieves better performance then deep learning based stock price forecasting existing methodologies © 2020 Seventh Sense Research Group® |
