SOLUTION: Forecasting Crude Oil Price Using ARIMA Model | My Assignment Tutor

Forecasting Crude Oil Price Using ARIMA ModelCrude oil is one of the most essential energy resources in our daily lives, ranging fromtransportation fuels to a wide range of production. Therefore, the fluctuations of crude oil pricehave a significant effect on worldwide economies and the cost of living. Political factors andother global issues impact the crude oil price such as the COVID-19 pandemic. If the priceforecasting in crude oil could be done through time series models, then the past behaviours ofcrude oil prices can forecast and explain the future prices with the available information. Inorder to reduce the risks and disadvantages related to the volatility in crude oil price, I wouldlike to carry out an analysis about the forecast in crude oil using ARIMA Model in this project.Four papers listed in the reference section are relevant to my research project. The firstpaper (Baumeister & Kilian, 2012) constructs a monthly real-time dataset for forecasting the realprices of crude oil from a variety of models. It helps generate reliable forecasts by removing theeffects of inflation and other factors. The second paper (He, 2018) identifies the best model forforecasting crude oil price by comparing SES, MA, ARIMA against SVR models over the time period2009 to 2017. Although this paper concludes more remarks regarding SVR model optimization, thecontrast reflects that ARIMA model gives more accurate forecasting result on crude price. It supportsme to conduct an analysis using ARIMA model which fits the testing data set based on estimatedparameters. The third paper (Selvi, Shree & Krishnan, 2018) construct the time series models forforecasting the price by using Box-Jenkins Methodology. It is found that ARIMA is a useful techniquesin forecasting and the price changes in the past are categorized into different stages. It providesknowledge of evaluating future price changes based on the past behaviours or factors with the useof ARIMA model. The last paper (Shah & Kiruthiga, 2020) collects the crude oil data of WestTexas Intermediate (WTI) from the period of 1987 to 2020 and processes the data by usingDickey-Fuller test for stationarity. It is useful because data preprocessing for ARIMA Model isneeded. For example, the data has to be examined the stationarity and decomposed into trendand seasonality.ReferencesBaumeister, C., & Kilian, L. (2012). Real-Time Forecasts of the Real Price of Oil. Journal of Business &Economic Statistics, 30(2), 326-336. Retrieved from http://www.jstor.org/stable/23243728He, Xin James (2018). Crude Oil Prices Forecasting: Time Series vs. SVR Models. Journal ofInternational Technology and Information Management, Vol 27 Issue: 02 , Article 2.Retrieved from https://core.ac.uk/download/pdf/212814404.pdfSelvi, J.J., Shree, R.K.& Krishnan, J. (2018). Forecasting Crude Oil Price Using ARIMA Models.International Journal of Advance Research in Science and Engineering, Vol. 07 Issue: 05. ISSN:2319-8354. Retrieved fromhttp://www.ijarse.com/images/fullpdf/1522053404_NIMT185ijarse.pdfShah, Jessin & Kiruthiga, G. (2020). Crude Oil Price Forecasting using ARIMA model. InternationalResearch Journal of Engineering and Technology, Vol. 07 Issue: 03. ISSN: 2395-0056.Retrieved from https://www.irjet.net/archives/V7/i3/IRJET-V7I31061.pdf