PREDICTING CRISES ON THE AFRICAN FRONTIER STOCK MARKETS WITH INVESTOR SENTIMENT INDICATORS: A MACHINE LEARNING APPROACH
Domaine:
socioeconomicType de record:
paper
Créateur:
DavLor
Éditeur:
Joh
Hôte:
This study examined the predictive ability of machine learning algorithms in identifying crises within African stock markets. The study employed seven distinct machine-learning models, analyzing historical stock prices from eight stock markets, three major sentiment indicators, and the exchange rates of local currencies against the US dollar, with each data spanning from May 1, 2007, to April 1, 2023. Extreme Gradient Boosting (XGBoost) emerged as the most effective algorithm for predicting crises. Historical stock prices and exchange rates were identified as the most critical features for prediction. On the sentiment side, investors’ perceptions of potential volatility on the S&P 500, as captured by the CBOE Volatility Index (VIX), and the daily News Sentiment Index were recognized as significant predictors.The study advances the understanding of market sentiment’s role in stock market dynamics and highlights the importance of employing advanced computational techniques for risk management and market stability.
Similaires
Investor sentiment, optimism and excess stock market returns. Evidence from emerging marketsEffect of presidential elections on investor herding behaviour in African stock marketsMachine Learning and Macroeconomic Indicators for Predicting Consumer Goods Stock Prices in NigeriaPredicting stock market crashes on the African stock markets: evidence from log-periodic power law modelSome evidence from a principal component approach to measure a new investor sentiment index in the Tunisian stock marketPresidential election uncertainty and investor overconfidence bias in sub-Saharan African stock markets