Application of Fuzzy Logic in Stock Markets by Using Technical Analysis Indicators

Abstract

Investing with proper understanding on the stock is risk taking, while investing based on rumor is gambling. Increase in retail investors during the pandemic gives an opportunity of a more volatile market, therefore it leads to a need of using proper tools to screen through the stock market to find worthy assets to invest in. Previous research shows that there are possibilities of utilizing artificial intelligence techniques in assessing the market performance such as utilizing genetic algorithm with moving average convergence-divergence to generate trading signals or using deep recurrent neural network with closing data to predict the next day stock price. Even though there are good algorithms out there, it has not been utilized and made available to the public to access. Therefore, this project aims to develop an application to screen through the market using artificial intelligence techniques such as fuzzy logic to find a company which is worthy to invest in. Historical price data from 100 companies that made up the Kuala Lumpur Composite Index (KLCI) is used to assess the performance of the fuzzy logic application developed. The technical indicators used for the system is RSI, stochastic and MACD. The trading strategy using this application is to select stocks which have score lower than 0.5 for a buy signal. The results almost achieve the primary objective of generating 70% correct buy signals for short-term trading.