Deep Candlestick Predictor: A Framework toward Forecasting the Price Movement from Candlestick Charts

Abstract

Candlestick charts have been very important tools for human traders to make trading decisions since 18th century which traders could recognize visual patterns from charts so that they can have more information when predicting price movements of financial products. Based on this idea, this paper proposed a deep network framework Deep Candlestick Predictor DCP to forecast the price movements by reading the candlestick charts rather than the numerical data from financial reports. DCP contains a chart decomposer which can decomposes the given a candlestick chart into several sub-charts, an CNN-Autoencoder which can derive the best representation for sub-charts, and a 1D-CNN which can to forecast the price movements of the (k+1)-th day. Extensive experiments are conducted by daily prices from real dataset of 6 merchandises in Taiwan Stock Exchange Capitalization Weighted Stock Index, which totally have 21,819 trading days. The experimental results show that the proposed framework DCP could achieve higher accuracy than the conventional index-based model, which shows the effectiveness of the concept of designing a deep network to read candlestick charts like human beings.