Stock Price Prediction in Indonesia's Mining Sector Using a Hybrid Conv1D-LSTM Model

Dublin Core

Title

Stock Price Prediction in Indonesia's Mining Sector Using a Hybrid Conv1D-LSTM Model

Subject

Deep Learning, Conv1D, LTSM, MiningStock Price,Prediction

Description

In the investment world, the ability to predict stock price movements is a key factor for success among investors and analysts. This study introduces a novel approach for forecasting stock prices in Indonesia's mining sector using a hybrid model that combines Convolutional Neural Networks (Conv1D) and Long Short-Term Memory (LSTM) networks. The volatile nature of stock markets and the unique characteristics of the mining industry demand accurate prediction models. Our research demonstrates that the Conv1D-LSTM model can extract patterns from stock price data more effectively than traditional models, thanks to Conv1D's feature extraction capabilities and LSTM's sequence learning strengths. By employing historical stock data from several leading mining companies in Indonesia, our model achieved a 15% higher prediction accuracy compared to conventional methods. These results highlight the significant potential of artificial intelligence in assisting investors to make more precise and informed decisions. We hope this research will pave the way for broader adoption of technology in the financial sector, especially in predicting complex and challenging market dynamics

Creator

Hamzah

Source

https://ijicom.respati.ac.id/index.php/ijicom/article/view/85/56

Date

August 2024

Contributor

fajar bagus W

Format

PDF

Language

English

Type

Text

Files

Collection

Citation

Hamzah, “Stock Price Prediction in Indonesia's Mining Sector Using a Hybrid Conv1D-LSTM Model,” Repository Horizon University Indonesia, accessed April 4, 2025, https://repository.horizon.ac.id/items/show/8396.