Can technical analysis create returns for beta-based portfolios in the Indian market?

The implementation of tools such as Genetic Algorithms has not been exploited for asset price prediction despite their power, robustness, and potential application in the stock market. This paper aims to fill the gap existing in the literature on the use of Genetic Algorithms for predicting asset pricing of investment strategies into stock markets and investigate its advantages over its peers Buy & Hold and traditional technical analysis. The Genetic Algorithms strategy applied to the MACD was carried out in two different validation periods and sought to optimize the parameters that generate the buy-sell signals. The performance between the machine learning-based approach, technical analysis with the MACD and B&H was compared. The results suggest that it is possible to find optimal values of the technical indicator parameters that result in a higher return on investment through Genetic Algorithms, beating the traditional technical analysis and B&H by around 4%. This study offers a new insight for practitioners, traders, and finance researchers to take advantage of Genetic Algorithms for trading rules application in forecasting financial asset returns under a more efficient and robust methodology based on historical data analysis.

The purpose of the study was to analyze the effectiveness of technical trading strategies in trading stocks of selected Indian companies represented in the Nifty 50 Index. The research was done using secondary data from January 2022 to August 2022. Hourly share prices of 14 largest companies as per market capitalization from 14 different sectors from the Nifty 50 Index were considered as a part of the study. Simple Moving Average, Exponential Moving Average – Relative Strength Index and Bollinger Bands – Relative Strength Index – strategies considered in the study. It was found that strategy based on Bollinger Bands and Relative Strength Index performed the best. Performance was considered with respect to both the number of stocks having a net profit and the number of stocks that were able to outperform the buy-and-hold strategy for the time period considered. The study considered several combined strategies and performance indicators, whereas previous studies used limited indicators. Out of the 14 stocks considered, the Simple Moving Average strategy was able to generate net profit for 8 stocks and it outperformed the buy-and-hold strategy for 6 stocks, Exponential Moving Average – Relative Strength Index strategy generated net profit for 6 stocks and it outperformed the buy-and-hold strategy for 5 stocks, and the Bollinger Bands – Relative Strength Index generated net profit for 11 stocks and it outperformed the buy-and-hold strategy for 10 stocks. The Bollinger Bands – Relative Strength Index strategy was able to outperform as it was more dynamic and entered and exited positions actively.

In stock markets, technical analysis plays a vital role by offering valuable insights into price trends, patterns, and anticipated market movements, aiding investors in making well-informed decisions. This study employs bibliometric and topic modelling approaches on 589 English-language journal articles indexed in Scopus in the last two decades (from 2003 to 2023), exclusively focusing on technical analysis in stock markets. The keyword co-occurrence analysis identifies five topic clusters. The application of structural topic modelling also unravels five prominent thematic clusters, namely pattern-based forecasting, rule-based trading, algorithmic trading, techno-fundamental trading, and machine learning & sentiment analysis. The topic of pattern-based forecasting involves researching the application of various patterns or models to predict stock prices. Rule-based trading concentrates on utilizing technical analysis tools to generate buy and sell signals, aiming for profitability. The algorithmic trading cluster explores the use of algorithms to systematically execute buy and sell actions, especially in high-frequency trading scenarios. Techno-fundamental trading investigates the integration of both fundamental and technical analysis in trading and investment decisions. Lastly, machine learning & sentiment analysis focus on applying advanced machine learning techniques and sentiment analysis for predicting stock prices, highlighting the use of sophisticated methods in this domain. The three predominant topics in the dataset are "rule-based trading," "machine learning & sentiment analysis," and "algorithmic trading" constituting 26.79%, 23.52%, and 21.11% of the dataset, respectively. These findings underscore the prominence and significance of these themes within the context of the research domain.