An Integrated Hierarchical Temporal Memory Network for Continuous Multi-Interval Prediction of Stock Price Trends

Abstract

We propose an integrated hierarchical temporal memory (IHTM) network for continuous multi-interval prediction (CMIP) based on the hierarchical temporal memory (HTM) theory. The IHTM network is constructed by introducing three kinds of new modules to the original HTM network. One is Zeta1FirstNode which is used to cooperate with the original HTM node types for predicting stock price with multi-interval at any given time. The second is Shift-VectorFileSensor module used for inputting stock price data to the network continuously. The third is a MultipleOutputEffector module which produces multiple prediction results with different intervals simultaneously. With these three new modules, the IHTM network make sure newly arriving data is processed and continuous multi-interval prediction is provided. Performance evaluation shows that the IHTM is efficient in the memory and time consumption compared with the original HTM network in CMIP.