Showing papers on "Volatility (finance) published in 2020"

COVID-19 Pandemic, Oil Prices, Stock Market, Geopolitical Risk and Policy Uncertainty Nexus in the US Economy: Fresh Evidence from the Wavelet-Based Approach

Abstract: In this paper, we analyze the connectedness between the recent spread of COVID-19, oil price volatility shock, the stock market, geopolitical risk and economic policy uncertainty in the US within a time-frequency framework. The coherence wavelet method and the wavelet-based Granger causality tests applied to US recent daily data unveil the unprecedented impact of COVID-19 and oil price shocks on the geopolitical risk levels, economic policy uncertainty and stock market volatility over the low frequency bands. The effect of the COVID-19 on the geopolitical risk substantially higher than on the US economic uncertainty. The COVID-19 risk is perceived differently over the short and the long-run and may be firstly viewed as an economic crisis. Our study offers several urgent prominent implications and endorsements for policymakers and asset managers

Empirical Asset Pricing via Machine Learning

Abstract: We perform a comparative analysis of machine learning methods for the canonical problem of empirical asset pricing: measuring asset risk premia. We demonstrate large economic gains to investors using machine learning forecasts, in some cases doubling the performance of leading regression-based strategies from the literature. We identify the best performing methods (trees and neural networks) and trace their predictive gains to allowance of nonlinear predictor interactions that are missed by other methods. All methods agree on the same set of dominant predictive signals which includes variations on momentum, liquidity, and volatility. Improved risk premium measurement through machine learning simplifies the investigation into economic mechanisms of asset pricing and highlights the value of machine learning in financial innovation.

Oil price news and COVID-19—Is there any connection?

Abstract: We evaluate the relative importance of COVID-19 infections and oil price news in influencing oil prices. We show that when the number of new COVID-19 infections surpasses 84,479, COVID-19 exerts a bigger effect on oil prices. Oil price news when conditioned on COVID-19 cases have limited effects on price. When oil price volatility is used as a threshold, at higher levels of volatility, both COVID-19 cases and negative oil price news influence oil prices.

Hourly Oil Price Volatility: The Role of COVID-19

Abstract: In this paper, we study the evolution of hourly oil price volatility. Using multiple measures of oil price volatility, we conclude that volatility increased following the onset of COVID-19. After controlling for conventional predictors of oil price volatility, we show that COVID-19 cases and deaths led to an increase in daily oil price volatility by between 8% and 22%. Our results pass a battery of robustness tests.

Fractional Neuro-Sequential ARFIMA-LSTM for Financial Market Forecasting

Abstract: Forecasting of fast fluctuated and high-frequency financial data is always a challenging problem in the field of economics and modelling. In this study, a novel hybrid model with the strength of fractional order derivative is presented with their dynamical features of deep learning, long-short term memory (LSTM) networks, to predict the abrupt stochastic variation of the financial market. Stock market prices are dynamic, highly sensitive, nonlinear and chaotic. There are different techniques for forecast prices in the time-variant domain and due to variability and uncertain behavior in stock prices, traditional methods, such as data mining, statistical approaches, and non-deep neural networks models are not suited for prediction and generalized forecasting stock prices. While autoregressive fractional integrated moving average (ARFIMA) model provides a flexible tool for classes of long-memory models. The advancement of machine learning-based deep non-linear modelling confirms that the hybrid model efficiently extracts profound features and model non-linear functions. LSTM networks are a special kind of recurrent neural network (RNN) that map sequences of input observations to output observations with capabilities of long-term dependencies. A novel ARFIMA-LSTM hybrid recurrent network is presented in which ARFIMA model-based filters having the linear tendencies better than ARIMA model in the data and passes the residual to the LSTM model that captures nonlinearity in the residual values with the help of exogenous dependent variables. The model not only minimizes the volatility problem but also overcome the over fitting problem of neural networks. The model is evaluated using PSX company data of the stock market based on RMSE, MSE and MAPE along with a comparison of ARIMA, LSTM model and generalized regression radial basis neural network (GRNN) ensemble method independently. The forecasting performance indicates the effectiveness of the proposed AFRIMA-LSTM hybrid model to improve around 80% accuracy on RMSE as compared to traditional forecasting counterparts.

A Note on the Asian Market Volatility During the COVID-19 Pandemic

Abstract: This paper provides a note on commonality in volatility for five developed Asian economies, namely Hong Kong, Japan, Russia, Singapore and South Korea. Additionally, we examine whether the COVID-19 pandemic changed the commonality in volatility within the Asian region. Overall, we find that commonality in volatility during the COVID-19 period is more prominent in the case of Singapore compared to other four economies.

COVID-19 and Stock Market Volatility

Abstract: I investigate the impact of COVID-19 cases and related deaths on the US stock market (Dow Jones and S&P500 indices), allowing for changes in trading volume and volatility expectations, as well as day-of-the-week effects. The results, based a GARCH(1,1) model and data from April 8, 2019 to April 9, 2020, suggest that changes in the number of cases and deaths in the US and six other countries majorly affected by the COVID-19 crisis do not have an impact on the US stock market returns, apart from the number of reported cases for China. However, there is evidence of a positive impact, for some countries, on the conditional heteroscedasticity of the Dow Jones and S&P500 returns. VAR models suggest that the number of reported deaths in Italy and France have a negative impact on stock market returns, and a positive impact on the VIX returns. Finally, Markov-Switching models suggest that at the end of February 2020 the magnitude of the negative impact of the VIX on stock market returns increased threefold.

COVID-19: The reaction of US oil and gas producers to the pandemic

Abstract: In this paper, we examine the reaction of US oil and gas producers to the COVID-19 pandemic. We find that firms react to COVID-19 heterogeneously. The pandemic significantly explains 28% of returns and 27% of return volatility. These findings are qualitatively consistent when using competing COVID-19 indicators.

Uncertainty Due to Infectious Diseases and Energy Market Volatility

Abstract: Motivated by the COVID-19 pandemic, we examine the role of uncertainty due to infectious diseases in predicting energy market volatility using the new dataset on Equity Market Volatility-Infectious Diseases (EMV-ID). We find that the new measure of market uncertainty is a good predictor of energy market volatility in both in-sample and out-of-sample tests. These results have implications for portfolio diversification strategies, which we set aside for future research.

Deep Reinforcement Learning for Trading

Abstract: In this article, the authors adopt deep reinforcement learning algorithms to design trading strategies for continuous futures contracts. Both discrete and continuous action spaces are considered, and volatility scaling is incorporated to create reward functions that scale trade positions based on market volatility. They test their algorithms on 50 very liquid futures contracts from 2011 to 2019 and investigate how performance varies across different asset classes, including commodities, equity indexes, fixed income, and foreign exchange markets. They compare their algorithms against classical time-series momentum strategies and show that their method outperforms such baseline models, delivering positive profits despite heavy transaction costs. The experiments show that the proposed algorithms can follow large market trends without changing positions and can also scale down, or hold, through consolidation periods. TOPICS:Futures and forward contracts, exchanges/markets/clearinghouses, statistical methods, simulations Key Findings • In this article, the authors introduce reinforcement learning algorithms to design trading strategies for futures contracts. They investigate both discrete and continuous action spaces and improve reward functions by using volatility scaling to scale trade positions based on market volatility. • The authors discuss the connection between modern portfolio theory and the reinforcement learning reward hypothesis and show that they are equivalent if a linear utility function is used. • The authors back test their methods on 50 very liquid futures contracts from 2011 to 2019, and their algorithms deliver positive profits despite heavy transaction costs.

Uncertainty and crude oil market volatility: new evidence

Abstract: The main goal of this paper is to investigate the predictability of five economic uncertainty indices for oil price volatility in a changing world. We employ the standard predictive regression fram...

Gold volatility prediction using a CNN-LSTM approach

Abstract: Prediction of volatility for different types of financial assets is one of the tasks of greater mathematical complexity in time series prediction, mainly due to its noisy, non-stationary and heteroscedastic structure. On the other hand, gold is an asset of particular importance for hedging and diversification of investment portfolios, and therefore it is important to predict future volatility of this asset. This paper seeks to significantly improve the forecast of gold volatility by combining two deep learning methodologies: short-term memory networks (LSTM) added to convolutional neural networks (specifically a pre-trained VGG16 network). It is important to mention that these types of hybrid architectures have not been used in time series prediction, so it is a completely new approach to solving these types of problems. The CNN-LSTM hybrid model is capable of including images as input which provides a wide variety of information associated with both static and dynamic characteristics of the series. In parallel, different lags of profitability of the series are entered as input, which allows it to learn from the temporal structure. The results show a substantial improvement when this hybrid model is compared to the GARCH and LSTM models. A 37% reduction in MSE is observed compared to the classic GARCH model, and 18% compared to the LSTM model. Finally, the Model Confidence Model (MCS) determines a significant improvement in the prediction of the hybrid model. The fundamental importance of this research lies in the application of a new type of architecture capable of processing various sources of information for any time series prediction task.

An evaluation of global organic aerosol schemes using airborne observations

Abstract: . Chemical transport models have historically struggled to accurately simulate the magnitude and variability of observed organic aerosol (OA), with previous studies demonstrating that models significantly underestimate observed concentrations in the troposphere. In this study, we explore two different model OA schemes within the standard GEOS-Chem chemical transport model and evaluate the simulations against a suite of 15 globally distributed airborne campaigns from 2008 to 2017, primarily in the spring and summer seasons. These include the ATom, KORUS-AQ, GoAmazon, FRAPPE, SEAC4RS, SENEX, DC3, CalNex, OP3, EUCAARI, ARCTAS and ARCPAC campaigns and provide broad coverage over a diverse set of atmospheric composition regimes – anthropogenic, biogenic, pyrogenic and remote. The schemes include significant differences in their treatment of the primary and secondary components of OA – a “simple scheme” that models primary OA (POA) as non-volatile and takes a fixed-yield approach to secondary OA (SOA) formation and a “complex scheme” that simulates POA as semi-volatile and uses a more sophisticated volatility basis set approach for non-isoprene SOA, with an explicit aqueous uptake mechanism to model isoprene SOA. Despite these substantial differences, both the simple and complex schemes perform comparably across the aggregate dataset in their ability to capture the observed variability (with an R2 of 0.41 and 0.44, respectively). The simple scheme displays greater skill in minimizing the overall model bias (with a normalized mean bias of 0.04 compared to 0.30 for the complex scheme). Across both schemes, the model skill in reproducing observed OA is superior to previous model evaluations and approaches the fidelity of the sulfate simulation within the GEOS-Chem model. However, there are significant differences in model performance across different chemical source regimes, classified here into seven categories. Higher-resolution nested regional simulations indicate that model resolution is an important factor in capturing variability in highly localized campaigns, while also demonstrating the importance of well-constrained emissions inventories and local meteorology, particularly over Asia. Our analysis suggests that a semi-volatile treatment of POA is superior to a non-volatile treatment. It is also likely that the complex scheme parameterization overestimates biogenic SOA at the global scale. While this study identifies factors within the SOA schemes that likely contribute to OA model bias (such as a strong dependency of the bias in the complex scheme on relative humidity and sulfate concentrations), comparisons with the skill of the sulfate aerosol scheme in GEOS-Chem indicate the importance of other drivers of bias, such as emissions, transport and deposition, that are exogenous to the OA chemical scheme.