A Comparative Analysis of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) Networks for Forecasting Stock Prices Over a One-Week Horizon at Yangon Stock Exchange

Kyaw Kyaw Khaing, Ah Nge Htwe, Andrew Lewis

Abstract: Stock price forecasting is a challenging task that has attracted considerable attention in financial research and machine learning applications. This study presents a comparison of two well-known neural network architectures, Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks. The two models are applied to predict stock values over one week. A sliding window approach is used for predicting future values. The performance of these models is assessed and compared based on the accuracy of their predictions of stock price data from Yangon Stock Exchange (YSX) Listed Companies. From experimental results, CNN appears to be more suitable for forecasting in emerging markets such as YSX.

External IDs:doi:10.1007/978-981-96-1531-5_45