Paper Key : IRJ************358
Author: Subir Gupta,Abhik Choudhary,Kamaluddin Mandal,Joyita Ghosh,Dipankar Roy
Date Published: 08 Jul 2024
Abstract
The financial market for silver is highly volatile and influenced by numerous economic factors, making accurate forecasting essential yet challenging for traders and policymakers. Traditional statistical models often fail to capture the complex, non-linear patterns in commodity trading. This study explores the application of Long Short-Term Memory (LSTM) models, a type of recurrent neural network, to improve the prediction accuracy of silver prices. An LSTM model is trained and tested by leveraging historical trading data, demonstrating superior performance in forecasting future price movements compared to traditional methods. The results indicate that LSTM models provide a robust framework for financial forecasting, enhancing decision-making and trading strategies in volatile markets. This research fills a gap by applying advanced machine learning techniques to the silver market, suggesting potential extensions to other commodities and financial instruments.
DOI LINK : 10.56726/IRJMETS60019 https://www.doi.org/10.56726/IRJMETS60019