Predicting the effect of Googling investor sentiment on Islamic stock market returns

Abstract

Purpose The purpose of this paper is to evaluate the capability of the hidden Markov model using Googling investors’ sentiments to predict the dynamics of Islamic indexes’ returns in the Middle East and North Africa (MENA) financial markets from 2004 to 2018. Design/methodology/approach The authors propose a hidden Markov model based on the transition matrix to apprehend the relationship between investor’s sentiment and Islamic index returns. The proposed model facilitates capturing the uncertainties in Islamic market indexes and the possible effects of the dynamics of Islamic market on the persistence of these regimes or States. Findings The bearish state is the most persistent sentiment with the longest duration for all the MENA Islamic markets except for Jordan, Morocco and Qatar. In addition, the obtained results indicate that the effect of sentiment on predicting the future Islamic index returns is conditional on the MENA States. Besides, the estimated mean returns for each state indicates that the bullish and calm states are ideal for investing in Islamic indexes of Bahrain, Oman, Morocco, Kuwait, Saudi Arabia and United Arab Emirates. However, only the bullish state is ideal for investing Islamic indexes of Jordan, Egypt and Qatar. Research limitations/implications This paper has used data at a monthly frequency that can explain only short-term dynamics between Googling investor’s sentiment and the MENA Islamic stock market returns. Moreover, this work can be done on the stock markets while taking into account the specificity of each activity sector. Practical implications In fact, the findings of this paper are helpful for academics, analysts and practitioners, and more specifically for the Islamic MENA financial investors. Moreover, this study provides useful insights not only into the duration of the relationship between the indexes’ returns and the investors’ sentiments in the five states but also into the transition probabilities which have implications for how investors could be guided in their choice of future investment in a portfolio with Islamic indexes. Findings of this paper are important and valuable for policy-makers and investors. Thus, predicting the effect of Googling investors’ sentiment on the MENA Islamic stock market dynamics is important for portfolio diversification by domestic and international investors. Moreover, the results of this paper gave new insights into financial analysts about the dynamic relationship between Googling investors’ sentiment and Islamic stock market returns across market regimes. Therefore, the findings of this study might be useful for investors as they help them capture the unobservable dynamics of the changes in the investors’ sentiment regimes in the MENA financial markets to make successful investment decisions. Originality/value To the best of the authors’ knowledge, this paper is the first to use the hidden Markov model to examine changes in the Islamic index return dynamics across five market sentiment states, namely the depressed sentiment (S1), the bullish sentiment (S2), the bearish sentiment (S3), the calm sentiment (S4) and the bubble sentiment (S5).

The impact of Coronavirus (COVID-19) outbreak on faith-based investments: An original analysis

“…For example, Trichilli et al (2020a) investigated the portfolio optimization under investor’s sentiment states of Hidden Markov model; and find that the Bayesian efficient frontier of Islamic and conventional stock portfolios is affected by the investor’s sentiment state and the time horizon. In a separate study, Trichilli et al (2020b) also examined the capability of the hidden Markov and investor sentiments to predict the dynamics of Islamic index’ returns in the Middle East and North Africa (MENA) financial markets. They find that the effect of sentiment on predicting the future Islamic index returns is conditional on the MENA region.…”

Predicting financial market returns in the presence of health crisis: evidence from conventional and Islamic stock markets

“…Jawadi et al (2020) indicate that the information for investor attention can be useful for developing prediction for Islamic stock returns. Trichilli et al (2020a) examined the investor sentiment for portfolio optimisation using Hidden Markov and Bayesçi models. According to the study results, the effective boundary of Islamic and conventional stock portfolios is affected by the investor sentiment and the time horizon.…”

Ensemble Technique With Optimal Feature Selection for Saudi Stock Market Prediction: A Novel Hybrid Red Deer-Grey Algorithm

“…In 2020, Trichilli et al [2] have introduced a HMM-based on transition matrix to investigate the relationship between the Islamic index returns and the investor's sentiment in MENA countries. The transition matrix and the steady-state probabilities were estimated using the HMM.…”

“…This makes the use of machine learning models for stock forecasting with the training of price fluctuations of days and even the minute. Models like RNN, HMM [2] [6] are more common in forecasting stock prices. To be more accurate, the Metaheuristic tactics are incorporated with the learning algorithm [6].…”