Stock Price Predictor: Implementing Stocks Predictive Model Using Deep Learning

Abstract

Purpose  – This paper proposes a novel deep neural network model, specifically long short-term memory (LSTM) networks, for predicting stock prices using historical data and financial indicators. 

Method – LTSM can handle long sequences while capturing temporal dependencies, making it an excellent choice for NLP or time series. The model is trained and tested on the Ayala Corporation (AYALY) stock dataset from 2016 to 2019, using four financial indicators: earnings per share (EPS), EPS growth, price/earnings ratio, and price/earnings-to-growth ratio.

Results – The results show that the model achieves high accuracy and outperforms other Deep Neural Network variants as confirmed by assessing its performance using suitable metrics like mean squared error and mean absolute error. It effectively explored and selected relevant financial indicators, implemented data preprocessing techniques, and trained the model using historical data.

Conclusion – The project effectively explored and selected relevant financial indicators and trained LSTM models using historical data, and, thus, met its objectives to develop a deep neural network model for stock price prediction.

Recommendations – The authors recommend that future researchers continue to explore the integration of a diverse set of financial indicators, employ rigorous comparative analyses, and experiment with different time frames for future predictions to further enhance prediction accuracy.

Research Implications – This paper contributes to the ongoing development of machine-learning studies, especially in the Philippines, particularly for time-series forecasting. With more accurate predictions of stock prices, the study could enable investors to make informed investment decisions, trading strategies, and financial decision-making processes.