ENHANCING STOCK PORTFOLIO PERFORMANCE USING MARKOV-SWITCHING MODELS AND CANDLESTICK PATTERNS FOR LONG-TERM INVESTMENT

Islamic stocks in Indonesia face challenges in portfolio management due to the limited number of issuers and low diversification. The change in market regime from bullish to bearish makes the portfolio more vulnerable, especially since some investors do not understand the concept of portfolio and the importance of determining optimal asset weighting. In addition, the allocation strategy used tends to be static and minimizes the utilization of sharia-based technical analysis, making investment decisions less responsive to market dynamics. This study aims to compare the performance of two portfolio allocation algorithms, which integrate Markov-switching models and Heiken Ashi candlestick patterns for trend identification, respectively. The research method used is a quantitative approach with experimental techniques or computational simulations that aim to test the performance of the algorithm in producing optimal portfolio weights. The portfolio model developed is an extension of the Markowitz model with two different integration approaches, namely the Markov-switching model and the Heiken Ashi candlestick pattern. Portfolio weight optimization on each algorithm is performed using the Generalized Reduced Gradient (GRG) method. The Markov-switching model is a time series model used to identify changes in the average market regime. In contrast, the Heiken Ashi pattern is used to detect trend changes in stock price movements. The time series data used consists of daily stock prices of Islamic stocks listed in the Jakarta Islamic Index (JII) during the period January 2019 to August 2022, obtained from the Indonesia Stock Exchange (IDX). This study finds that the Markowitz model integrated with the Markov-switching model is able to effectively identify market regimes and improve efficiency in portfolio weight optimization. These findings provide valuable insights for Islamic equity investors in their risk mitigation efforts while helping to align expected returns with long-term investment strategies that are adaptive to bullish and bearish market conditions.