Paper Contents
Abstract
Financial markets are highly dynamic, where stock price prediction has always been a challenging task due to non-linear patterns, noise, and external influences. Traditional time-series models fail to capture complex dependencies, while deep learning models provide improved forecasting power. This research presents a hybrid Multi-Layer Perceptron (MLP) and Long Short-Term Memory (LSTM) model for predicting stock price trends using historical data and technical indicators such as Moving Averages, RSI, MACD, and Bollinger Bands. The proposed approach is compared with standalone MLP and LSTM models. Experimental results indicate that the hybrid MLP-LSTM achieves superior accuracy, lower error rates, and more stable predictions, highlighting its potential for real-world financial forecasting.Keywords: Stock Prediction, MLP, LSTM, Technical Indicators, Deep Learning, Time Series Forecasting, Financial Market
Copyright
Copyright © 2025 SURYA K M. This is an open access article distributed under the Creative Commons Attribution License.
