Machine learning, oil prices and cryptocurrencies

Springer has published a new Open Access article which looks at the role of cryptocurrencies and the US dollar in predicting oil prices pre and during COVID-19 pandemic.

Between January 2018 and July 2021, the study used three machine learning models to explore the turbulent crude oil markets in the context of global instability under COVID-19. The team also looked at two similarly unstable cryptocurrencies (Bitcoin and Ethereum) which experienced losses similar to those felt by the oil industry.

The long study period was implemented to “decrease the bias and the misspecification errors produced by the parametric models”.

The three models were: 1) Support Vector Machines 2) Multilayer Perceptron Neural Networks and 3) Generalised Regression Neural Networks (GRNN).

The three researchers (Bassam A. Ibrahim, Ahmed A. Elamer and Hussein A. Abdou) reported that:

Bitcoin is “the most influential in predicting oil prices” before COVID-19 and during the downtrend during COVID-19, with Ethereum becoming “the most influential during the bull oil market” during COVID-19.
COVID-19 variables became “the most influential during the uptrend”, especially the number of death cases.
GRNN is the most accurate model to predict the price of oil under the conditions of uncertainty that prevailed in the world during this period. They also noted that (the best prediction model under normal conditions before COVID-19 during an uptrend was SVM and during a downtrend was GRNN.

Other factors they note include Tesla cancelling dealing in Bitcoin, Tesla’s reasoning citing the use of fossil fuels in mining, and the fact Bitcoin was banned in China during the study period.

The researchers were confident that their results have provided “crucial evidence” for investors, academics and policymakers, especially during global uncertainties and particularly when trying to escape a crash in the markets.

Investors may wish to consider mixing cryptocurrencies and crude oil prices for portfolio hedging and trading strategies during future crises similar to the COVID-19 outbreak.