Learning from multivariate discrete sequential data using a restricted Boltzmann machine model
This work addresses the limitation of RBMs for sequential data analysis, which is incremental as it extends an existing model for time-series prediction in finance.
The paper tackled the problem of modeling dynamic data like time-series with restricted Boltzmann machines (RBMs), which lack memory, by proposing a p-RBM model that retains memory of p past states, and tested it on predicting NASDAQ-100 stock directions, showing promising prediction potential.
A restricted Boltzmann machine (RBM) is a generative neural-network model with many novel applications such as collaborative filtering and acoustic modeling. An RBM lacks the capacity to retain memory, making it inappropriate for dynamic data modeling as in time-series analysis. In this paper we address this issue by proposing the p-RBM model, a generalization of the regular RBM model, capable of retaining memory of p past states. We further show how to train the p-RBM model using contrastive divergence and test our model on the problem of predicting the stock market direction considering 100 stocks of the NASDAQ-100 index. Obtained results show that the p-RBM offer promising prediction potential.