Forecasting commodity prices: empirical evidence using deep learning tools.

Since the last two decades, financial markets have exhibited several transformations owing to recurring crises episodes that has led to the development of alternative assets. Particularly, the commodity market has attracted attention from investors and hedgers. However, the operational research stream has also developed substantially based on the growth of the artificial intelligence field, which includes machine learning and deep learning. The choice of algorithms in both machine learning and deep learning is case-sensitive. Hence, AI practitioners should first attempt solutions related to machine learning algorithms, and if such solutions are unsatisfactory, they must apply deep learning algorithms. Using this perspective, this study aims to investigate the potential of various deep learning basic algorithms for forecasting selected commodity prices. Formally, we use the Bloomberg Commodity Index (noted by the Global Aggregate Index) and its five component indices: Bloomberg Agriculture Subindex, Bloomberg Precious Metals Subindex, Bloomberg Livestock Subindex, Bloomberg Industrial Metals Subindex, and Bloomberg Energy Subindex. Based on daily data from January 2002 (the beginning wave of commodity markets' financialization) to December 2020, results show the effectiveness of the Long Short-Term Memory method as a forecasting tool and the superiority of the Bloomberg Livestock Subindex and Bloomberg Industrial Metals Subindex for assessing other commodities' indices. These findings is important in term for investors in term of risk management as well as policymakers in adjusting public policy, especially during Russian-Ukrainian war.

The Influence of Economic Policy Uncertainty and Business Cycles on Fine Wine Prices.

This study investigates the impact of both economic policy uncertainty (EPU) and business cycles on the fine wine market. We use a nonlinear autoregressive distributed lag model to measure the influence of these two variables on three major Liv-ex indices over the period 2005M01-2020M12. Our results are multiple. First, fine wine prices are relatively unaffected asymmetrically by EPU, while the economic cycle has a more pronounced asymmetric effect, especially in the short run. Second, uncertainty in Europe and the USA affect fine wine prices more than in China. Third, in the short term, fine wine prices react more strongly to changes in business cycles than to uncertainty. Finally, prices of the five first growths of Bordeaux are asymmetrically influenced by EPU, unlike of the rest of the most prestigious Bordeaux wines. The study also has implications for investment. We argue that a strong and professional strategic intelligence watch would help stakeholders in the secondary wine market to improve their returns, especially when European and US wines are involved. While short-runners should focus on information relative to changes in the business cycle, long-term investors would find it more interesting to closely monitor policy decisions liable to have long-term effects on wine prices (such as taxation, monetary measures…).

The Brexit impact on European market co-movements.

The aim of this paper is to investigate the impact of Brexit on the dependence between European financial markets. We use the Diebold and Yilmaz (2009, 2012) approach to better map the relationship between the three main European markets and we propose an Optimal portfolio weighting to gain insights into the portfolio design dynamics in the period between 2013 and 2019, in particular any changes due to uncertainty surrounding Brexit. First, the findings show that between September 2015 and September 2016, the high level of volatility and spillover confirms the strong degree of market integration, with uncertainty surrounding the referendum outcome having a clear impact on the three main European markets. Second, the direction of spillover in the pre-Brexit period was from the UK market to the French and German markets in anticipation of uncertainty regarding the outcome of the referendum and the period immediately following it. Third, only the conditional correlation between the pair (CAC40-FTSE100) is characterized by an asymmetric effect.

Cryptocurrency volatility forecasting: What can we learn from the first wave of the COVID-19 outbreak?

This study aims to examine the issue of cryptocurrency volatility modelling and forecasting based on high-frequency data. More specifically, this study assesses whether crisis periods, particularly the coronavirus disease pandemic, influence the dynamic of cryptocurrency volatility. We investigate the four main cryptocurrency markets (Bitcoin, Ethereum Classic, Ethereum, and Ripple) from April 2018 to June 2020. The realized volatility measure is computed and decomposed to various components (continuous versus discontinuous, positive and negative semi-variances, and signed jumps). A variety of heterogeneous autoregressive (HAR) models are developed including these components, thereby enabling assessment of different assumptions (including persistence and asymmetric dynamic) of modelling and volatility forecasting based on in-sample and out-of-sample forecasting strategies, respectively. Our results reveal three main findings. First, the extended HAR model that includes the positive and negative jumps appears to be the best model for predicting future volatility for both crisis and non-crisis periods. Second, during the crisis period, only the negative jump component is statistically significant. Third, in terms of volatility forecasting, the results show that the extended HAR model that includes positive and negative semi-variances outperform the other models.

Does non-fundamental news related to COVID-19 matter for stock returns? Evidence from Shanghai stock market.

The COVID-19 outbreak generates various types of news that affect economic and financial systems. No studies have assessed the effects of such news on financial markets. This study sheds light on the impact of non-fundamental news related to the COVID-19 pandemic on the liquidity and returns volatility. Because we examined extreme events, we performed quantile regression on daily data from December 31, 2019 to the end of lockdown restrictions in China on April 7, 2020. Results showed that the non-fundamental news, as the number of deaths and cases related to the COVID-19, raised the stock market returns volatility and reduced the level of stock market liquidity, increasing overall risk, whereas fundamental macroeconomic news remained largely immaterial for the stock market. These findings are explained by a knock-on effect because the health system's inability to manage and treat a high number of COVID-19 patients in intensive care led the country to implement a lockdown and the global economy to largely shut down.