AAU Student Projects - visit Aalborg University's student projects portal
A master's thesis from Aalborg University
Book cover


Predicting The EUR/USD Exchange Rate: A Deep Learning Approach

Term

4. term

Education

Publication year

2024

Submitted on

Pages

117

Abstract

This thesis leverages the Long Short-Term Memory (LSTM) neural network, known for its efficiency in time-series predictions and long-term dependencies, to forecast FOREX market directions. By integrating macroeconomic data and technical indi- cators into a selection of alternative LSTM models, our approach can be thought of as a starting point of employing more complex versions to more accurately predict daily deviations in the currencies pairs of the FOREX market or any other financial market. The paper presents the different building blocks necessary to understand the deep neural network framework more in-depth.