Multi-model Learning Methods for Oil Price Prediction
Subhani Shaik
Department of Information Technology, Sreenidhi Institute of Science and Technology (Autonomous), Hyderabad, India.
A. Sreeja *
Department of Information Technology, Sreenidhi Institute of Science and Technology (Autonomous), Hyderabad, India.
B. Spoorthi
Department of Information Technology, Sreenidhi Institute of Science and Technology (Autonomous), Hyderabad, India.
Saniya Noorin
Department of Information Technology, Sreenidhi Institute of Science and Technology (Autonomous), Hyderabad, India.
*Author to whom correspondence should be addressed.
Abstract
Present-day oil prices are rising due to certain conditions like inflation entire world. It is a major problem in the world. It affects so many fields connected to human life. Oil price prediction is most important for business scenarios. Machine learning algorithms play a key role in oil price prediction. Machine learning models predict the price of fuel. This paper aims to compare the machine learning models with multi-model learning models. To know in terms of accuracy and performance. Ensemble machine learning algorithms are most adaptive for different environments. The predicted price of crude oil in the future is decided using machine learning algorithms. In our research, we tested five models for calculating oil price prediction. Among these five models, tuning three models with hyperparameters. Hyperparameter tuning means AutoML, which boosts the performance of the models. The above three models’ performance shows more than 93%. Two models, support vector machine and linear regression, do not perform well. The accuracy rate is more than 50%.
Keywords: Automatic machine learning, oil prices prediction, hybrid machine learning