Stock trading system using fuzzy candlesticks and reinforcement learning

One commonly used technical analysis is the candlestick charts. By studying historical stock data in candlestick charts, experts hypothesize and propose patterns that can predict price trends ahead. Inspired by this methodology, fuzzy logic is generally used to model raw stock data into fuzzy can...

Full description

Saved in:
Bibliographic Details
Main Author: Lee, Wen Chong
Other Authors: Quek Hiok Chai
Format: Final Year Project
Language:English
Published: 2018
Subjects:
Online Access:http://hdl.handle.net/10356/76213
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-76213
record_format dspace
spelling sg-ntu-dr.10356-762132023-03-03T20:53:46Z Stock trading system using fuzzy candlesticks and reinforcement learning Lee, Wen Chong Quek Hiok Chai School of Computer Science and Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence One commonly used technical analysis is the candlestick charts. By studying historical stock data in candlestick charts, experts hypothesize and propose patterns that can predict price trends ahead. Inspired by this methodology, fuzzy logic is generally used to model raw stock data into fuzzy candlesticks, providing autonomous predictions. Most literature that used this approach tries to model existing patterns established by experts. The objective of this research is to discover candlestick patterns and propose a trading system that takes advantage of these patterns. Firstly, the necessity of expert knowledge is circumvented by discovering candlestick patterns using genetic algorithm. A trading system that incorporates the top performing patterns is then developed and used to evaluate their competence. Additionally, an experiment is conducted to determine the potential of using fuzzy candlesticks and the discovered patterns in a reinforcement learning technique (Double Deep Q-Network). The results of the experiments show promise for this novel approach. The discovered patterns have an accuracy rate of approximately 70 – 80%. Furthermore, the trading system is found to do remarkably better when trading with multiple stocks. With the proposed trading systems, the performance of trading with 28 stocks from the S&P 500 index outdoes the average return rate. Bachelor of Engineering (Computer Science) 2018-12-03T14:52:10Z 2018-12-03T14:52:10Z 2018 Final Year Project (FYP) http://hdl.handle.net/10356/76213 en Nanyang Technological University 60 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
spellingShingle DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Lee, Wen Chong
Stock trading system using fuzzy candlesticks and reinforcement learning
description One commonly used technical analysis is the candlestick charts. By studying historical stock data in candlestick charts, experts hypothesize and propose patterns that can predict price trends ahead. Inspired by this methodology, fuzzy logic is generally used to model raw stock data into fuzzy candlesticks, providing autonomous predictions. Most literature that used this approach tries to model existing patterns established by experts. The objective of this research is to discover candlestick patterns and propose a trading system that takes advantage of these patterns. Firstly, the necessity of expert knowledge is circumvented by discovering candlestick patterns using genetic algorithm. A trading system that incorporates the top performing patterns is then developed and used to evaluate their competence. Additionally, an experiment is conducted to determine the potential of using fuzzy candlesticks and the discovered patterns in a reinforcement learning technique (Double Deep Q-Network). The results of the experiments show promise for this novel approach. The discovered patterns have an accuracy rate of approximately 70 – 80%. Furthermore, the trading system is found to do remarkably better when trading with multiple stocks. With the proposed trading systems, the performance of trading with 28 stocks from the S&P 500 index outdoes the average return rate.
author2 Quek Hiok Chai
author_facet Quek Hiok Chai
Lee, Wen Chong
format Final Year Project
author Lee, Wen Chong
author_sort Lee, Wen Chong
title Stock trading system using fuzzy candlesticks and reinforcement learning
title_short Stock trading system using fuzzy candlesticks and reinforcement learning
title_full Stock trading system using fuzzy candlesticks and reinforcement learning
title_fullStr Stock trading system using fuzzy candlesticks and reinforcement learning
title_full_unstemmed Stock trading system using fuzzy candlesticks and reinforcement learning
title_sort stock trading system using fuzzy candlesticks and reinforcement learning
publishDate 2018
url http://hdl.handle.net/10356/76213
_version_ 1759853674157309952