مجلة الاقتصاد والتنمية المستدامة
Volume 9, Numéro 1, Pages 134-150
2026-03-01

Gold Price Prediction Based On Arima And Lstm Neural Network



Authors : Mohammed Rouaba .

Abstract

This study compares the forecasting performance of the Autoregressive Integrated Moving Average (ARIMA) model and the Long Short-Term Memory (LSTM) neural network in predicting daily closing prices of gold. Using a dataset covering the period from January 1, 2023, to May 25, 2025, both models were implemented in Python and evaluated using standard error metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). The ARIMA model was constructed following differencing and optimal order selection based on the Akaike Information Criterion. The LSTM model employed a multi-layer architecture refined through experimental trials. Results indicate that the ARIMA model outperformed the LSTM network across all metrics, suggesting its greater suitability for modeling short-term gold price movements in this context.

Keywords

Gold price forecasting ; ARIMA ; LSTM ; Time series ; financial modeling

Les articles similaires

Gold Price Forecasting Using Stacked Lstm Neural Networks: A Deep Learning Approach

Belgat Amira . 
pages 775-788.

Stock Price Prediction To Support Investment Decisions: A Model Based On Lstm Networks

Berboucha Meriem . 
pages 103-119.

Forecasting Government Final Consumption Expenditure In Algeria: Comparative Performance Of The Arima (box-jenkins) Model And Artificial Neural Networks (mlp & Lstm) Up To 2034

Lagoune Salim . 
pages 13-27.

Deformation Analysis Of Gps Auscultation Network Based On Generalized Regression Neural Network (grnn )

Gourine B . 
pages 139-160.

مقارنة بين نموذج Var و Arima للتنبؤ بالتضخم في الجزائر Comparison Of The Var And Arima Model For Inflation Prediction In Algeria

بلحاج عمارة شهرزاد . 
ص 383-394.

Formats de citation