Encoding Candlesticks as Images for Patterns Classification Using Convolutional Neural Networks

01/16/2019
by   Yun-Cheng Tsai, et al.
0

Candlestick charts display the high, low, open and closing prices for a specific time series. Candlestick patterns emerge because human actions and reactions are patterned and continuously replicate and captured in the formation of the candles. According to Thomas Bulkowski's Encyclopedia of Candlestick Charts, there are 103 candlestick patterns. Traders use these patterns to determine when to enter and exit. However, the candlestick patterns classification takes the hard work out of identifying them visually. In this paper, we propose an extend Convolutional Neural Networks (CNN) approach "GASF-CNN" to recognize the candlestick patterns automatically. We use the Gramian Angular Field (GAF) to encode the time series as different types of images. Then we use the CNN with the GAF encoding images to learn eight critical kinds of candlestick patterns. The simulation and experimental results evidence that our approach can find the eight types of candlestick patterns over eighty percent accuracy automatically.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/02/2017

Classification of Time-Series Images Using Deep Convolutional Neural Networks

Convolutional Neural Networks (CNN) has achieved a great success in imag...
research
04/26/2022

Encoding Cardiopulmonary Exercise Testing Time Series as Images for Classification using Convolutional Neural Network

Exercise testing has been available for more than a half-century and is ...
research
06/02/2020

Identification of hydrodynamic instability by convolutional neural networks

The onset of hydrodynamic instabilities is of great importance in both i...
research
01/21/2022

Dynamic Deep Convolutional Candlestick Learner

Candlestick pattern is one of the most fundamental and valuable graphica...
research
03/28/2023

Combinatorial Convolutional Neural Networks for Words

The paper discusses the limitations of deep learning models in identifyi...
research
03/26/2020

Triad State Space Construction for Chaotic Signal Classification with Deep Learning

Inspired by the well-known permutation entropy (PE), an effective image ...
research
12/08/2017

Mining Fix Patterns for FindBugs Violations

In this paper, we first collect and track large-scale fixed and unfixed ...

Please sign up or login with your details

Forgot password? Click here to reset