On the volatility of WTI crude oil prices: A time-varying approach with stochastic volatility

This study investigates the impacts of crude oil-market-specific fundamental factors and financial indicators on the realized volatility of West Texas Intermediate (WTI) crude oil price. A time-varying parameter vector autoregression model with stochastic volatility (TVP-VAR-SV) is applied to weekly data series spanning January 2008 to October 2021. It is found that the WTI oil price volatility responds positively to a shock in oil production, oil inventories, the US dollar index, and VIX but negatively to a shock in the US economic activity. The response to the EPU index was initially positive and then turned slightly negative before fading away. The VIX index has the most significant effect. Furthermore, the time-varying nature of the response of the WTI realized oil price volatility is evident. Extreme effects materialize during economic recessions and crises, especially during the COVID-19 pandemic. The findings can improve our understanding of the time-varying nature and determinants of WTI oil price volatility. © 2022

Machine Learning Algorithm on Assets' Behaviour During and Post Covid Pandemic

Global financial assets behaviour has become highly volatile during the pandemic period, especially the highly risky assets. Financial instruments like cryptocurrencies are basically speculative and the investors basically trade on these anomalies. Even though the entire world has come to standstill these markets were never. In order to understand the market anomalies during the COVID pandemic the popular asset in cryptos which is bitcoin along with the global market index such as S&P 500, Global Crude Oil prices and gold prices daily trading data are taken into consideration during and post covid. Some of the interesting aspects of Machine Learning (ML) such as variety of techniques, parameter selection, nonlinearity and generalization ability make it well suited for the problems of uncertain functional structure. Price prediction of stock markets is a challenging problem because of unpredictable noise and the number of potential variables that may impact on the prices. The research work presented in this paper involves the development of a ML algorithm which will throw light on the price behaviour of these instruments during and post crisis. © 2022 WMSCI.All rights reserved.