Wavelet-enhanced multimodel framework for stock market forecasting: A comprehensive analysis across market regimes

This paper explores how the returns of country exchange traded funds (ETFs) respond to global risk factors in different market regimes. We consider the ETFs for the U.S., Canada, U.K., Germany, France, Italy, Japan, and Australia from May 30, 2000 to March 31, 2011. To answer this question, we use the Bayesian information criterion to select a regime switching model (RS) with six global risk factors and identify three market regimes - bull, transitory and bear markets. The empirical results show that both the returns of country ETFs and their sensitivities to the risk factors are highly regime dependent. First, the U.S. size and value factors are significant in explaining most of selected ETFs across regimes. More specifically, small capitalization is associated with lower returns for all country ETFs (except for Canada) in at least one market regime. High book-to-market ratio generates higher returns for all ETFs in most market regimes. Second, the global stock market return has a positive impact on the returns of all country ETFs. Third, all ETFs returns are negatively correlated with market volatility in bull and bear market regimes. Fourth, a stronger U.S. dollar generates a higher return for the U.S. ETF and lower returns for the other seven country ETFs across market regimes. Finally, the returns of Australia, Canada and U.K. ETFs, which invest heavily in materials, are positively correlated with commodity prices while other country ETF returns are negatively associated with these prices across market regimes.

Relationship between green investments, energy markets, and stock markets in the aftermath of the global financial crisis

ABSTRACTWe investigate the effects of China’s official interest rate changes on its stock market. We first prove there is a negative relationship between official rate changes and stock returns, as measured by cumulative abnormal returns (CARs). Then, we divide the Chinese stock market into three regimes (bull, medium, and bear) and indicate that official rate changes have asymmetric effects on CARs during different market regimes, although these effects differ from the effects of interest rate changes on the U.S. market. Specifically, official rate changes have the largest negative effects during bear markets and the smallest effects during medium markets.

We investigate the dynamic behaviour of conditional correlations between the US market, gold and two gold financial proxies using a multivariate dynamic conditional correlation model over different market regimes. A comprehensive period of time is analysed covering approximately 37 years of daily data, from August 1976 to March 2013, as well as a shorter period, of about 15 years, from September 1998 to March 2013. Both periods include the recent sub-prime financial crisis. Market regimes are defined using bull/bear states and alternatively using volatility regimes from a three-state Markov-switching variance model. An index of US mining companies and a value-weighted portfolio of US gold mutual funds are treated as potential proxies for an investment in gold. Two important conclusions emerge from our study. The first is that, even in the context of a dynamic correlation analysis, gold is always a safe haven; negatively correlated with the stock market under adverse market conditions. The second is that, although the gold proxies considered here exhibit a low correlation with the stock market and therefore offer diversification benefits, they cannot be considered perfect substitutes of gold due to their lack of negative correlations with the market in times of turmoil.

This study’s aim is to investigate systemic risk in the Chinese stock market. To this end, we analyze risk contributions to the Chinese stock market from 2007 to 2018 at the sector level using the Conditional Value at Risk (CoVaR) approach proposed by Adrian and Brunnermeier (2016). For the full sample period, we find that the information technology sector is the top contributor to systemic risk in the Chinese stock market. To distinguish the risk contribution of each sector under different market regimes, we propose an adjusted Bry-Boschan program to identify turning points in the stock market, which captures regime shifting between bull and bear markets. We find that the risk contribution of each sector in a bear market is significantly higher than that in the following bull market. We also find that the top contributor to systemic risk in the Chinese stock market changes across market regimes. Our findings have important policy implications. First, policymakers may use the early identification of systemically risky sectors of the stock market to improve the pertinence of economic policy-making. Second, it may allow security regulators to foster an environment in which incentives for risk taking by financial practitioners are reduced.

This study seeks to investigate the spillover effects between uncertainty indexes and returns on African stock markets; explore the time-varying nature of these interactions using TVP-VAR and QVAR techniques; and assess the resilience of individual stock markets to shocks, with particular attention to Energy Policy Uncertainty (EPU), Climate Policy Uncertainty (CPU), and Geopolitical Risks (GPRs) indexes. Accordingly, we employed two novel techniques, namely QVAR and TVP-VAR connectedness approaches to ascertain interdependencies under the bearish, bullish, and normal market regimes. The results for the QVAR approach revealed a total connectedness index (TCI) of 89.5%, suggesting substantial co-movement across markets during bearish market regime. Total connectedness index increased marginally to 89.7% under the bullish regime, reflecting an adaptive shift in shock propagation. Results from the TVP-VAR technique show a TCI of 71.97%, an indication of a reduced market interconnectedness amidst normal market regimes. We observe that CPU, EPU, and GPRs displayed heterogeneous spillover effects, with EPU and GPRs presenting pressing risks for majority of the markets. Additionally, the markets exhibited varying degrees of resilience under the various regimes, providing valuable insights for investors and policymakers on the nuances of the African stock market and shocks across various market regimes.

This study uses the hidden Markov model (HMM) to identify different market regimes in the US stock market and proposes an investment strategy that switches factor investment models depending on the current detected regime. We first backtested an array of different factor models over a roughly 10.5 year period from January 2007 to September 2017, then we trained the HMM on S&P 500 ETF historical data to identify market regimes of that period. By analyzing the relationship between factor model returns and different market regimes, we are able to establish the basis of our regime-switching investing model. We then back-tested our model on out-of-sample historical data from September 2017 to April 2020 and found that it both delivers higher absolute returns and performs better than each of the individual factor models according to traditional portfolio benchmarking metrics.

This paper critically examines artificial intelligence applications in stock market forecasting, addressing significant gaps in the existing literature that often overlook the tension between theoretical market efficiency and empirical predictability. While numerous reviews catalog methodologies, they frequently fail to rigorously evaluate model performance across different market regimes or reconcile statistical significance with economic relevance. We analyze techniques ranging from traditional statistical models to advanced deep learning architectures, finding that ensemble methods like Extra Trees, Random Forest, and XGBoost consistently outperform single classifiers, achieving directional accuracy of up to 86% in specific market conditions. Our analysis reveals that hybrid approaches integrating multiple data sources demonstrate superior performance by capturing complementary market signals, yet many models showing statistical significance fail to generate economic value after accounting for transaction costs and market impact. By addressing methodological challenges including backtest overfitting, regime changes, and implementation constraints, we provide a novel comprehensive framework for rigorous model assessment that bridges the divide between academic research and practical implementation. This review makes three key contributions: (1) a reconciliation of the Efficient Market Hypothesis with AI-driven predictability through an adaptive market framework, (2) a multi-dimensional evaluation methodology that extends beyond classification accuracy to financial performance, and (3) an identification of promising research directions in explainable AI, transfer learning, causal modeling, and privacy-preserving techniques that address current limitations.

Market regimes are a critical factor influencing stock price fluctuations. We observe that regime characteristics can be reflected in the dynamic variations in the strength of multiple inter-stock relationships. However, existing methodologies predominantly rely on a single graph constructed using prior knowledge or directly infer a singular type of relationship from time series data. These approaches fail to account for the existence of multiple types of relationships and their dynamic variations in strength. To address this limitation, we propose a novel framework, the Dual-Path Adaptive-Correlation Spatial-Temporal Inverted Transformer (DPA-STIFormer), which decouples time series data to learn diverse types of relationships and introduces a gated mechanism to adaptively fuse them, thereby accommodating different market regimes. Experiments conducted on four stock market datasets demonstrate state-of-the-art performance, with an average improvement of over 5%, validating the model’s superior capability in uncovering latent temporal-correlation patterns.

This paper proposes a dynamic herding approach which takes into account herding under different market regimes, with concentration on the Gulf Arab stock markets – Abu Dhabi, Dubai, Kuwait, Qatar and Saudi Arabia. Our results support the presence of three market regimes (low, high and extreme or crash volatility) in those markets with the transition order ‘low, crash and high volatility’, suggesting that these frontier markets have a different structure than developed markets. The results also yield evidence of herding behavior under the crash regime for all of the markets except Qatar which herds under the low and high volatility regimes. The findings of the cross-GCC herding model also demonstrate herding comovements and not spillovers and are also robust to the cross-GCC volatility shocks. The tests that underline the cross volatility shocks generally suggest that the crash regime is a true regime and not a statistical artifact. Policy and portfolio diversification implications are discussed.

This paper addresses the interpretability problem of non-parametric option pricing models by using the explainable artificial intelligence (XAI) approach. We study call options written on the S&P 500 stock market index across three market regimes: pre-COVID-19, COVID-19 market crash, and post-COVID-19 recovery. Our comparative option pricing exercise demonstrates the superiority of the random forest and extreme gradient boosting models for each market regime. We also show that the model’s pricing accuracy has worsened from the pre-COVID-19 to the recovery period. Moneyness was the most important price determinants across the market regimes, while the implied volatility and time-to-maturity inputs contributed intermittently to a lesser extent. During the COVID-19 crash, open interest gained more economic importance due to the increased behavioral tendencies of traders consistent with market distress.

Fraud on the market: A relational investment approach

This paper presents a categorical review of existing literature in the field of share market forecasting. Share market forecasting has been done in econometrics and statistics for quite some time and the emergence of artificial intelligence and data mining are giving new dimensions to it. Data mining is being used in modern day to mine terabytes of data to find new and useful patterns from existing data for the betterment of the society. One of the application of data is to mine the data regarding the stocks in the public domain and help investors formulate a decision. We have conducted an extensive review of existing literature regarding the use of data mining techniques on the domain of share market forecasting and propose a new framework for real time stock price forecasting.

Impacts of oil shocks on stock markets in Norway and Japan: Does monetary policy's effectiveness matter?

Hedge ratio on Markov regime-switching diagonal Bekk–Garch model