Restricted Boltzmann Machine Based Stock Market Trend Prediction

For the past decades, stock prediction has been a popular topic in financial applications. Many approaches including machine learning based and statistical models have been employed to forecast price changes in stock market. Considering the power of Restricted Bolztmann Machine (RBM) for feature extraction, we propose to incorporate RBM and several classifiers to predict short-term stock market trend. In this paper, eleven technical indicators are firstly inferred by using trading data, e.g., close price, lowest price, open price and highest price. Afterwards, these technical indicators are conveyed to binary values by using a trend deterministic preparation layer. We apply a RBM to extract features from binary valued features from the last step. The experimental study demonstrates this model's effectiveness compared with several traditional methods.