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.

Time-Series Analysis and Healthcare Implications of COVID-19 Pandemic in Saudi Arabia.

The first case of coronavirus disease 2019 (COVID-19) in Saudi Arabia was reported on 2 March 2020. Since then, it has progressed rapidly and the number of cases has grown exponentially, reaching 788,294 cases on 22 June 2022. Accurately analyzing and predicting the spread of new COVID-19 cases is critical to develop a framework for universal pandemic preparedness as well as mitigating the disease's spread. To this end, the main aim of this paper is first to analyze the historical data of the disease gathered from 2 March 2020 to 20 June 2022 and second to use the collected data for forecasting the trajectory of COVID-19 in order to construct robust and accurate models. To the best of our knowledge, this study is the first that analyzes the outbreak of COVID-19 in Saudi Arabia for a long period (more than two years). To achieve this study aim, two techniques from the data analytics field, namely the auto-regressive integrated moving average (ARIMA) statistical technique and Prophet Facebook machine learning technique were investigated for predicting daily new infections, recoveries and deaths. Based on forecasting performance metrics, both models were found to be accurate and robust in forecasting the time series of COVID-19 in Saudi Arabia for the considered period (the coefficient of determination for example was in all cases more than 0.96) with a small superiority of the ARIMA model in terms of the forecasting ability and of Prophet in terms of simplicity and a few hyper-parameters. The findings of this study have yielded a realistic picture of the disease direction and provide useful insights for decision makers so as to be prepared for the future evolution of the pandemic. In addition, the results of this study have shown positive healthcare implications of the Saudi experience in fighting the disease and the relative efficiency of the taken measures.

Analysis and modeling of COVID-19 epidemic dynamics in Saudi Arabia using SIR-PSO and machine learning approaches.

INTRODUCTION: COVID-19 has become a global concern because it has extensive damage to health, social and economic systems worldwide. Consequently, there is an urgent need to develop tools to understand, analyze, monitor and control further outbreaks of the disease. METHODOLOGY: The Susceptible Infected Recovered-Particle SwarmOptimization model and the feed-forward artificial neural network model were separately developed to model COVID-19 dynamics based on daily time-series data reported by the Saudi authorities from March 2, 2020 to February 21, 2021. The collected data were divided into training and validation datasets. The effectiveness of the investigated models was evaluated by using various performance metrics. The Susceptible-Infected-Recovered-Particle-Swarm-Optimization model was found to well predict the cumulative infected and recovered cases and to optimally tune the contact rate and the characteristic duration of the illness. The feed-forward artificial neural network model was found to be efficient in modeling daily new and cumulative infections, recoveries and deaths. RESULTS: The forecasts provided by the investigated models had high coefficient of determination values of more than 0.97 and low mean absolute percentage errors (around 7% on average). CONCLUSIONS: Both the Susceptible-Infected-Recovered-Particle-Swarm-Optimization and feed-forward artificial neural network models were efficient in modeling COVID-19 dynamics in Saudi Arabia. The results produced by the models can help the Saudi health authorities to analyze the virus dynamics and prepare efficient measures to control any future occurrence of the epidemic.

Generalized Richards model for predicting COVID-19 dynamics in Saudi Arabia based on particle swarm optimization Algorithm.

COVID-19 pandemic is spreading around the world becoming thus a serious concern for health, economic and social systems worldwide. In such situation, predicting as accurately as possible the future dynamics of the virus is a challenging problem for scientists and decision-makers. In this paper, four phenomenological epidemic models as well as Suspected-Infected-Recovered (SIR) model are investigated for predicting the cumulative number of infected cases in Saudi Arabia in addition to the probable end-date of the outbreak. The prediction problem is formulated as an optimization framework and solved using a Particle Swarm Optimization (PSO) algorithm. The Generalized Richards Model (GRM) has been found to be the best one in achieving two objectives: first, fitting the collected data (covering 223 days between March 2nd and October 10, 2020) with the lowest mean absolute percentage error (MAPE = 3.2889%), the highest coefficient of determination (R2 = 0.9953) and the lowest root mean squared error (RMSE = 8827); and second, predicting a probable end date found to be around the end of December 2020 with a projected number of 378,299 at the end of the outbreak. The obtained results may help the decision-makers to take suitable decisions related to the pandemic mitigation and containment and provide clear understanding of the virus dynamics in Saudi Arabia.