Comparative Analysis of Deep Learning Models for Silver Price Prediction: CNN, LSTM, GRU and Hybrid Approach

Abstract

In this study, the performance of different deep learning algorithms to predict silver prices was evaluated. It was focused on the use of deep learning models such as CNN, LSTM, and GRU for the prediction process, as well as a new hybrid model based on combining these models. Each algorithm was trained on historical silver price data and compared its performance in price prediction using this data. This approach aims to achieve more comprehensive and accurate forecasts by combining the strengths of each model. It also makes a unique contribution to the literature in this area by addressing a specialized area such as the silver market, which is often neglected in financial forecasting. The study presents an innovative approach to financial forecasting and analysis methodologies, highlighting the advantages and potential of deep learning models for time-series data processing. The results compare the ability of these algorithms to analyze silver prices based on historical data only and to assess past trends. The study showed that these algorithms exhibit different performances in analyzing historical data. In conclusion, this study compared the performance of different deep learning algorithms for predicting silver prices based on historical data and found that the CNN-LSTM-GRU hybrid model has the potential to make better predictions. These results can provide guidance to researchers working on financial analysis and forecasting.