Presentation Type
Oral
Student
Yes
Track
Other
Abstract
Abstract
While studies on global oil price variability, occasioned by OPEC crude oil supply, is well documented in energy literature; the impact assessment of non-OPEC global oil supply on price variability, on the other hand, has not received commensurate attention. Given this gap, the primary objective of this study, therefore, is to estimate the magnitude of oil price determinism that is explained by the share of non-OPEC’s global crude oil supply. Using secondary sources of data collection method, data for target variable will be collected from the US Federal Reserve, as it relates to annual crude oil price variability, while data for the two explanatory variables of OPEC oil supply, and non-OPEC oil supply will be gathered from the OPEC Annual Statistical Bulletin.
The dataset so generated will covers the period from 2000 to 2022 using the supervised Machine Learning Random Forest Model in scientific writing. To assess the performance of this model, the collected data will be shuffled and split into two parts with the help of the train-test-split function in the Scikit-learn library. While the study, among the many determinants of oil price variability, is limited to only two explanatory variables of OPEC and non-OPEC oil supply, it is the expectation of the study to isolate, and see what magnitude of price variability that is explained by non-OPEC supply behavior. The accuracy of the model preliminary shows a test result of about 0.96 with an F1_score value of 0.88.
Keywords: Variability, behavior, determinism, oil price, oil supply
Start Date
2-6-2024 2:30 PM
End Date
2-6-2024 3:30 PM
Included in
Computer Sciences Commons, Data Science Commons, Mathematics Commons
Session 8: Machine Learning based Behavior of Non-OPEC Global Supply in Crude Oil Price Determinism
Dakota Room 250 A/C
Abstract
While studies on global oil price variability, occasioned by OPEC crude oil supply, is well documented in energy literature; the impact assessment of non-OPEC global oil supply on price variability, on the other hand, has not received commensurate attention. Given this gap, the primary objective of this study, therefore, is to estimate the magnitude of oil price determinism that is explained by the share of non-OPEC’s global crude oil supply. Using secondary sources of data collection method, data for target variable will be collected from the US Federal Reserve, as it relates to annual crude oil price variability, while data for the two explanatory variables of OPEC oil supply, and non-OPEC oil supply will be gathered from the OPEC Annual Statistical Bulletin.
The dataset so generated will covers the period from 2000 to 2022 using the supervised Machine Learning Random Forest Model in scientific writing. To assess the performance of this model, the collected data will be shuffled and split into two parts with the help of the train-test-split function in the Scikit-learn library. While the study, among the many determinants of oil price variability, is limited to only two explanatory variables of OPEC and non-OPEC oil supply, it is the expectation of the study to isolate, and see what magnitude of price variability that is explained by non-OPEC supply behavior. The accuracy of the model preliminary shows a test result of about 0.96 with an F1_score value of 0.88.
Keywords: Variability, behavior, determinism, oil price, oil supply