Investigation Into The Effectiveness Of Long Short Term Memory Networks For Stock Price Prediction

Stock prices are a form of time series data. There have been many existing business and economics based methods for predicting stock prices. These methods can be classed as fundamental and technical analysis. Technical analysis is based on the observing patterns in stock prices based on psychological effects (fear and greed) changing supply and demand. Fundamental analysis is based on observing current news and events such as the corporate profits and economic situation. However, all of these models ultimately rely on human judgement of the situation to make predictions and are not learned [1].