Stock Market Behaviour Prediction using Stacked LSTM Networks

Predicting the behavior of the stock market has been an area that has attracted the interest of many researchers particularly in the field of Machine Learning and time series analysis. The ability to analyse an entity such as the stock market that appears to lack synchronicity yet seemingly influenced by historic events remains an open issue in research. This study adopts a stacked Long Short Term Memory network model for predicting stock market behabiour. The data used is composed of historic stock market data from the American Stock Exchange, NASDAQ Composite (IXIC). Results obtained show that by making use of a stacked Long Stort Term Memory network model, future stock market behavior can be predicted.