LSTM-Based Gasoline Price Prediction - An Example of Gasoline 95# in Beijing

Abstract

Gasoline, as one of the indispensable energy sources in the global economy, the stability of its price has an important impact on national energy security and economic development. This study aims to improve the accuracy of gasoline price prediction through the use of Long Short-Term Memory Network (LSTM). By collecting and analyzing the historical price data of No. 95 gasoline in Beijing, the author constructed a prediction model based on LSTM, which is particularly suitable for dealing with long-term dependence in time series data. By comparing their performance to the traditional Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN), LSTM demonstrates its advantages in processing complicated time series data. The validity of the model is verified by several evaluation metrics, including mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). The results of the study indicate that the LSTM model shows high accuracy and reliability in predicting gasoline prices. In addition, future work will explore the introduction of multivariate analysis and hybrid network models to further the accuracy of the predictions and its generalization ability.