Automated Machine Learning and Asset Pricing

Characteristics of spillovers between the US stock market and precious metals and oil

Machine learning techniques for prediction and rule extraction from artificial neural network methods are used. The hypothesis that market sentiment and IPO specific attributes are equally responsible for first-day IPO returns in the US stock market is tested. Machine learning methods used are Bayesian classifications, support vector machines, decision tree techniques, rule learners and artificial neural networks. The outcomes of the research are predictions and rules associated With first-day returns of technology IPOs. The hypothesis that first-day returns of technology IPOs are equally determined by IPO specific and market sentiment is rejected. Instead lower yielding IPOs are determined by IPO specific and market sentiment attributes, while higher yielding IPOs are largely dependent on IPO specific attributes.

This paper examines the dynamic and switching effects of volatility spillovers arising from US stock market returns and GDP growth on those of Australia, Canada and the UK. For this purpose, we use quarterly data (1961q1–2013q1) and a constant probability Markov regime switching model. We found that the US stock market volatility significantly affects the stock market volatility of all three countries at least in one of the two specified regimes over time. However, the stock market volatilities in none of the three countries are contemporaneously influenced by the US output volatility even after allowing for two distinct regimes. On the other hand, the US stock market volatility exerts significant influences on the output volatilities of both Australia and the UK. Compared with Australia and the UK, Canada and the US show substantial output volatility co-movements, thereby confirming the close association between the two neighbouring economies through the NAFTA (North American Free Trade Agreement). We conclude that shocks emanating from the US stock market have unequivocal flow-on effects on the output and return volatilities of the other economies.

Using the COVID-19 and the Sino-US trade war as the background, the data of the stock markets in China and the US from March 1, 2017 to September 11, 2020 are divided into 3 phases, and the high-frequency return series are extracted by empirical mode decomposition algorithm, excluding the interference of the medium-frequency data and low-frequency data. The DCC-GARCH model is used to analyze the China-US stock market linkage in the 3 phases, and the results show that: both the China-US trade war and the COVID-19 have a significant impact on the China-US stock market linkage. The Sino US trade war makes the linkage of Sino US stock market decline in the short term, while The COVID-19 made the relationship between China and the United States present an inverted “U” shape of first rising and then falling.

Purpose – This paper aims to employ GARCH-class models (GARCH, IGARCH and CGARCH) to estimate the volatility persistence on crude oil, US, Gulf Corporation Council (GCC), Brazil, Russia, India and China (BRIC) stock markets. Also, the paper investigates the volatility spillover and the dynamic conditional correlation between crude oil, US stock index and stock indices of GCC and BRIC countries. The results prove a high degree of volatility persistence in the crude oil and stock markets. Based on the BEKK-GARCH and DCC-GARCH results, the paper finds strong evidence of the contagion effect of the oil shock and US financial crisis of 2008 on GCC and BRIC stock markets. Design/methodology/approach – In the beginning, the paper uses univariate GARCH models to estimate the volatility persistence of the oil market, US stock market, and GCC and BRIC stock markets. Then, the paper uses a trivariate BEKK-GARCH model of Malik and Hammoudeh to examine the volatility spillover between oil market, US stock market and stock markets for GCC and BRIC countries. Finally, the paper analyses the dynamic conditional correlation between US market and each stock market of GCC and BRIC countries using the DCC-GARCH model. Also, the paper estimates the dynamic conditional correlation between oil market and all stock markets. Findings – The results indicate the contagion effect of the oil shock and US financial crisis of 2008 on the GCC stock markets which are among the most important oil-exporting countries and also on BRIC stock markets which are among the emergent countries which are characterized by high economic growth level. Originality/value – The contribution of this paper is to investigate the existence of contagion effect between oil market, US stock market and two panels of emerging stock markets which have different economic characteristics, the GCC and BRIC countries, during the oil shock and US financial crisis period of 2008-2009.

The spillover effects and connectedness among green commodities, Bitcoins, and US stock markets: Evidence from the quantile VAR network

BackgroundBecause the movement of stock prices is not only ubiquitous in financial markets but also crucial for investors, extensive studies have been done to understand the law behind it. In particular, since the financial crisis in 2008, researchers have a more interest in investigating large market volatilities in order to grasp changing market trends.Methodology/Principal FindingsIn this work, we analyze the breakouts and breakdowns of both the Standard & Poor’s 500 Index in the US stock market and the Shanghai Composite Index in the Chinese stock market. The breakout usually represents an ongoing upward trend in technical analysis while the breakdown represents an ongoing downward trend. Based on the renormalization method, we introduce two parameters to quantize breakouts and breakdowns, respectively. We discover scaling behavior, characterized by power-law distributions for both the breakouts and breakdowns in the two financial markets with different power-law exponents, which reflect different market volatilities. In detail, the market volatility for breakdowns is usually larger than that for breakouts. Moreover, as an emerging market, the Chinese stock market has larger market volatilities for both the breakouts and breakdowns than the US stock market (a mature market). Further, the short-term volatilities show similar features for both the US stock market and the Chinese stock market. However, the medium-term volatilities in the US stock market are almost symmetrical for the breakouts and breakdowns, whereas those in the Chinese stock market appear to be asymmetrical for the breakouts and breakdowns.Conclusions/SignicanceThe methodology presented here provides a way to understand scaling and hence volatilities of breakouts and breakdowns in stock price dynamics. Our findings not only reveal the features of market volatilities but also make a comparison between mature and emerging financial markets.

This paper studies the feasibility of correlation-based investment strategies in the Chinese and US stock markets. After testing eight different correlations between returns and various factors under two different stock selection methods, the highest correlation is identified between returns and volatility under the Pearson correlation coefficient, in which the volatility is defined as the ratio of the differences between the maximum and minimum prices within two successive trading days. The investment strategies are investigated under two stock selection methods and three portfolio construction methods, and SSCI and S&P500 Index are chosen as benchmarks respectively. In the Chinese stock market the contrarian strategy obtain significant positive excess returns while in the US stock market the momentum strategy perform better. The results show that correlation-based investment strategy is more feasible in the Chinese stock market than in the US, and the US stock market is more efficient than the Chinese stock market.

The First 50 Years of the US Stock Market: New Evidence on Investor Total Return Including Dividends, 1793-1843

The 2008 global financial crisis provides us with a wide range of study fields on cross-asset contagion mechanisms in the US financial markets. After a decade of the so-called subprime crisis, the impact of market news on asset volatilities increased significantly. Consequently, return and volatility spillovers became the most extensive channel for spreading out the news generated in one market to the other ones, which made the financial markets inherit international risk factors as their own local risks. Moreover, as a result of the Chinese economy becoming the main driver of the global economy in the last decade, Chinese markets became more interconnected with developed markets which were followed by a “digital cold war” era via Twitter. In this study, we investigate the relationship between the US stock market, Chinese stock markets, rare earth markets and industrial metals, and mining products via three different models by utilizing VAR–VECH–TARCH models. According to our findings, bilateral spillover exists between US and Chinese stock markets. Cross-market spillovers show that there is a risk transmission channel between the industrial metals, rare earth, and Chinese and US stock markets due to China’s strengthening position in the global economy.

Subject. The global economic crisis of 2008, geopolitical crises between 2014 and 2023 and the socio-economic consequences of the COVID‑19 pandemic have a significant negative impact on the stock markets. The result of this influence is a significant increase in stock market volatility and instability. The purpose of the article is to develop a methodology for assessing thesustainability of the stock market and, on its basis, carrying out a comparative analysis of the sustainability of the stock markets of the Russian Federation and the USA. Methodology. Systematic and comparative analysis is used, as well as statistical methods and methods of the theory of cenoses. Scientific novelty: a dimensionless indicator of the stability of the economic system of stock market companies has been developed. Results. A methodology is proposed for assessing the sustainability of stock market issuing companies based on its model — economic cenosis. Within the framework of this methodology, a cenological analysis of structural changes and stability of the economic system under consideration is carried out. The developed methodology was tested based on the capitalization data of 100 companies listed on the Moscow Exchange and the S&P 500 index. A comparative analysis of the stability of the stock markets of the Russian Federation and the United States showed a sufficient degree of stability of the Russian stock market in relation to one of the most developed stock markets in the world — the US stock market. Conclusions. The proposed methodology makes it possible to assess the sustainability of the stock market as a unified economic system of issuing companies based on their key parameter — capitalization. Maximizing the sustainability indicator makes it possible to determine the potential investment valuation of the selected company shares, provided that the economic system of the stock market, in the process of its evolution, strives for its most stable state. Practical significance. The results and conclusions of the article may be in demand not only by regulatory organizations and stock market participants, but also by potential ordinary investors.

This paper is based on an investigation to explore the dynamic relationship between US stock market index and three other stock indices of the Middle East and North Africa (MENA). This is accomplished by using discrete wavelet filtering, applied to daily data set from 6/29/2001 to 5/5/2009. After that co integration test and VEC model are used to determine the long run and short run relationship between these stock markets. Co integration test confirms the existence of co integration between the studied series, and shows that there is a long run relationship between the US stock market and MENA stock markets, while the VEC model shows that there is a short run relationship between the aforesaid stock markets.

In this article, the co-movement between GCC and US stock market returns was investigated using the wavelet coherence method. The Dynamic Conditional Correlation GARCH (DCC-GARCH) modelling is then applied on time-varying components in order to provide a point of comparison with the results extracted from wavelet analysis. The investigation was conducted on the weekly stock index prices of two USA stock markets, namely Dow Jones and S&P 500 and six GCC stock markets, namely the United Arab Emirates, Saudi Arabia, Qatar, Oman, Kuwait, and Bahrain. The data were retrieved from Thomson Reuters's data stream and the sample duration was from 7 January 2007 to 24 June 2018. As a result, a definite co-movement between several GCC stock markets and those of the US stock markets for a long term was found. Moreover, the results also displayed signs of the significant disparity between the co-movements of the stock markets throughout the scales of time during economic decline. This phenomenon was possibly expected during the economic decline, where a significant divergence occurred as opposed to co-movement. The implications of the findings for global investors were considerable due to the indication from long-term co-movement that these investors would not be capable of gaining simultaneous profit from time and portfolio being diversified. In fact, the results showed the major difference in the opportunities for international portfolio diversification throughout these markets in terms of scale and time.

Studying the linkage between US and Chinese stock markets under the context of COVID-19 outbreak in 2020 can help us to prevent related financial risks, regulate corresponding monetary policies, and avoid the herd effect of investors being blindly optimistic or pessimistic. Between January 1, 2020 and November 10, 2022, using the returns of the S&P 500 index as a proxy for the US stock market and the CSI 300 index as a proxy for the Chinese stock market, the VAR-GARCH-BEKK model was used to empirically analyze the relationship between the two. According to the findings, the rise and fall of the S&P 500 index has some favorable effects on the rise and fall of the CSI 300 index. Yet, the CSI 300 index's movement is largely determined by past data, suggesting that the S&P 500's volatility, which represents the US stock market, has little effect on the Chinese stock market, which is represented by the CSI 300.

On the stability of long-run relationships between emerging and US stock markets