Forex Price Prediction Using Deep Learning and Comparative Analysis with Traditional Time Series Models

Akhtar, Hamza Pasking (2024) Forex Price Prediction Using Deep Learning and Comparative Analysis with Traditional Time Series Models. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

This research focuses on predicting Forex price trends by employing both traditional time series models and advanced deep learning techniques. The study utilizes traditional models such as ARIMA and SARIMA, alongside deep learning methodologies like Long Short-Term Memory (LSTM) which is implemented using TensorFlow and Keras frameworks. The primary objective is to explore and conduct a comparative analysis based on the performance of these models in capturing the complexities of a highly volatile Forex market and forecasting the price. The capabilities of LSTM have also been explored by adding several variations including hyperparameter tuning, integrate technical indicators (e.g., RSI, MACD, and Moving Average), and Bi-directional LSTM. The performance of these models is analysed using evaluation metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). The research reveals that among the models utilized, a fine-tuned LSTM has been able to outperform other models which showcase its ability in capturing intricate patterns. The execution time for the model shows that increase in model architecture increases execution time of that model. The insights from this research aims to contribute to the field of financial forecasting by offering different perspective on the strengths and limitations of different modelling approaches for Forex price prediction.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Yaqoob, Abid UNSPECIFIED
Uncontrolled Keywords:	ARIMA; SARIMA; Deep Learning; Long Short-Term Memory (LSTM); Bidirectional LSTM; Forex; Price Prediction; Technical indicators
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > Economics Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	01 Sep 2025 13:45
Last Modified:	01 Sep 2025 13:45
URI:	https://norma.ncirl.ie/id/eprint/8669

Actions (login required)

View Item