An Efficient Deep Learning Model for Stock Market Prediction
Molloy Faculty Mentor
Helen Dang
Presenter Major
Computer Science/ Mathematics
Presentation Type
Oral
Location
H339, 3rd floor, Barbara H. Hagan Center for Nursing
Start Date
28-4-2025 5:15 PM
End Date
28-4-2025 5:22 PM
Description (Abstract)
Stock market prediction is a complex problem due to the nonlinear and volatile nature of financial data. It is inherently a time series forecasting problem, where historical price patterns, trends, and market indicators are analyzed to predict future movements. Traditional models tend to struggle to take into account long-term dependencies. For that, deep learning techniques, particularly Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks, are valuable for improving forecast accuracy. This study applies a Deep Learning model and fine-tunes its parameters to predict stock prices. The performance of this model is also evaluated using real-world datasets and other model evaluation parameters.
Keywords
Stock Market Prediction, Deep Learning, Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Time Series Forecasting.
Related Pillar(s)
Study
An Efficient Deep Learning Model for Stock Market Prediction
H339, 3rd floor, Barbara H. Hagan Center for Nursing
Stock market prediction is a complex problem due to the nonlinear and volatile nature of financial data. It is inherently a time series forecasting problem, where historical price patterns, trends, and market indicators are analyzed to predict future movements. Traditional models tend to struggle to take into account long-term dependencies. For that, deep learning techniques, particularly Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks, are valuable for improving forecast accuracy. This study applies a Deep Learning model and fine-tunes its parameters to predict stock prices. The performance of this model is also evaluated using real-world datasets and other model evaluation parameters.
