Crude Oil Price Prediction using Embedding Convolutional Neural Network Model

Abstract

In this paper, a new crude oil price forecasting model using data embedding and Convolutional Neural Network has been proposed to predict more accurate crude oil price movement. It uses the time delayed embedding technique to transform the data into two-dimensional phase space. The Convolutional Neural Network model is used to extract the main data characteristics more effectively, taking advantage of the hierarchical feature extraction and modeling capability of CNN model. Empirical evaluation of the performance of the proposed TDE-CNN model has been conducted using daily price observations in West Taxes Intermediate market. Experiment results confirm that the TDE-CNN forecasting model produces forecasts with the improved forecasting accuracy.