Stock Price Prediction by Using BLSTM (Bidirectional Long Short Term Memory)

Abstract

Currently, many researchers are working on stock price prediction system by using deep learning algorithms. Stock market is completely random, and there is no pattern. Even though, a pattern in stock market could be found, it will not be last for a long time because the stock market will adopt a new situation and the strategy is no longer available on already changed stock market. There are many auto trading programs such as a trading bot on stock market. However, they are literally trade stocks based on human’s direction or rules. It will not affect any changes, and it keeps working as what rules are set up from the initial status on the stock market. Stock price depends on volume of total sales, stock news, revenue, total asset, big buyer’s position and so on. There are many aspects for affecting stock price, and it changes all the time. Therefore, it keeps monitoring stock market and makes a decision whether buy or sell at the right time for earning profits. This research uses Bidirectional Long Short-Term Memory (BLSTM) to predict stock price in the near future. BLSTM is more accurate than LSTM which is one directional. In addition, stock market is like a living creature. Data to manipulate stock price must be inputted and analyzed consistently. Therefore, stock price can be predicted by consistent monitoring with BLSTM.