Please use this identifier to cite or link to this item:
|Title:||Use of genetic programming to create technical trading rules||Authors:||Pranav Ramkumar.||Keywords:||DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
DRNTU::Engineering::Computer science and engineering::Software::Programming techniques
|Issue Date:||2009||Abstract:||There are two main schools of thought adopted by investors for trading in equity markets namely ‘Fundamental Analysis’ and ‘Technical Analysis’. While ‘Fundamental Analysis’ aims at predicting long-term fluctuations in the price of a stock by carefully examining the company's financials, operations, management and growth potential, ‘Technical Analysis’ is aimed at devising trading rules capable of exploiting short-term fluctuations on the financial markets. Recent results have indicated that the trading approach used by technical analysts which requires active buying and selling of securities over short time periods may be a viable alternative to the ‘buy and hold’ approach of fundamental analysts, where the assets are kept over a relatively long time period. However, the method adopted by each technical analyst for making a choice of trading rules for trading securities in his market of choice is entirely based on his anticipation of market movement and risk appetite. In this project, a Genetic Programming (GP) Paradigm developed in Java has been used to automatically generate trading rules for stock trading. The tree-like structure provided by GP provides a better representation of a composite trading rule comprised of different simple rules. Trading rules were developed for a portfolio of 30 stocks each from the FTSE 100 equity index of the UK and the Hang Seng equity index of Hong Kong, using historical pricing and transaction volume data. Rather than using a composite stock index, the trading rules are adjusted to individual stocks. The performance of these trading rules in comparison with the return from buy and hold approach as well as the returns from using Moving Average Convergence / Divergence (MACD), a simple technical indicator was studied.||URI:||http://hdl.handle.net/10356/16835||Rights:||Nanyang Technological University||Fulltext Permission:||restricted||Fulltext Availability:||With Fulltext|
|Appears in Collections:||SCSE Student Reports (FYP/IA/PA/PI)|
Updated on Dec 4, 2020
Updated on Dec 4, 2020
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.