International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 08 Issue: 07 | July 2021
p-ISSN: 2395-0072
www.irjet.net
A New Approach for Crude Oil Price Prediction based on FBprophet Prof. M.N. Galphade 1, Shivamkumar Khandagare2, Kumar Utkarsh3, Shailendra Kumar4 1Professor
Computer Department, SIT, LONAVALA Department, SIT, LONAVALA ---------------------------------------------------------------------***---------------------------------------------------------------------steady in early 2014, they fell sharply since mid 2014. Abstract - The volatility of crude oil market and its In January 2016, the U.S. refiner acquisition cost for chain effects to the global economy augmented the crude oil imports, as a proxy for world oil price, is interest and fear of individuals, public and private only $28.81 per barrel on an average, and the West sectors. Earlier statistical and econometric methods used Texas Intermediate (WTI) crude oil spot price, as the for prediction, offer good results when dealing with linear benchmark oil price in Northern America, is only data. However, crude oil price series deals with high non $31.68 per barrel on average. The prices have linearity and irregular events. The continuous usage of considerably dropped by more than 70 percent since statistical and econometric methods for crude oil price June 2014. prediction might demonstrate demotions to the crude oil price prediction performance. Time series forecasting The world's environment is badly affected by the oil through combination of historical quantitative data with price falling. With the drop of crude oil prices, the fuel qualitative data from experts view and news is a remedy bills are also lowered. As a result, consumers are very proposed to predict this. likely to use even more oil and hence they increase the carbon emission. In addition, there are less A time series is a set of observations taken at specific incentives to develop renewable and clean sources of time usually at equal intervals. ex-month, year, decade, energy. On the other hand, sustained low oil prices etc.. It is used to predict the future value based on the might result in considerable drop in global oil and gas previous observations. FBprophet is a procedure for exploration and exploitation activities. forecasting time series data based on additive model Fluctuating oil prices also play an important role in where non linear trends are fit with yearly, weekly and the world economy all over. The frequent fall in oil daily seasonality plus holiday effects. It works best with prices would result in the modest boost to global time series forecasting that have strong seasonal effect economic activity, but the owners of oil sectors and several seasons of historical data. It is robust to generally suffer income losses. Recent researches missing data and shifts in the trend and typically handles from the World Bank shows that for each 30% outliers well decline in oil prices, the global GDP (Gross Domestic Key Words: Crude oil, Prediction Model, Time series Product) would be increased by 0.5%. At the same forecasting ,FBprophet, machine learning. time, the drop of oil prices would also reduce the cost of living, and hence the inflation rate would also fall. 1.INTRODUCTION There is no doubt that crude oil price forecasts are very much useful to various industries, governments The paper is based on the design and application of organisations as well as individuals. Thus, forecasting Crude Oil Price Prediction using FBprophet model. crude oil prices have also been the subject of research Crude oil is a natural fossil fuel found in geological by both academia and industries. Many methods and formations beneath the earth's surface in fluid form. approaches have also been developed for predicting It has mostly been extracted by oil drilling, which crude oil prices. However, due to the higher volatility comes after the numerous studies of structural of oil prices, it remains one of the most challenging geology, sedimentary basin analysis, and reservoir prediction problems. characterization. Crude oil is among the most In recent years, forecasting techniques have been important energy resources on earth. So far, it used frequently in many applications in geosciences. remains the world's leading fuel, with nearly 1/3rd of Time series forecasting provides powerful global energy consumption all over. computational tools and powerful algorithms that Crude oil prices are determined by different factors can learn from past experiences and make and it has a big impact on the global environment and predictions on data. In this paper, we are proposing a even economy. Although crude oil prices were firm n novel approach for crude oil price prediction based 2,3,4Computer
© 2021, IRJET
|
Impact Factor value: 7.529
|
ISO 9001:2008 Certified Journal
|
Page 3704