Please use this identifier to cite or link to this item:
Title: Foreign exchange prediction using the long short-term memory neural network
Authors: Lee, Xiang Wei
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2018
Abstract: The foreign exchange market is one of the most active among other financial markets such as stocks and it has the highest amount of trading volume. With the advancement in technology, computer algorithm trading has become very common. The machine learning neural network could play an additional role in predicting the future prices of the foreign exchange market to make profit in the market. There are many kinds of machine learning neural network such as Artificial Neural Network (ANN), Support Vector Regression (SVR) and Recurrent Neural Network (RNN). However, the RNN is the most popular among the others. An extension of the RNN is the Long short-term memory neural network (LSTM) where it can solve the RNN vanishing gradient problem. Hence when it comes to recurrent neural network, LSTM is widely introduced and used. The aim of this paper is to evaluate the effectiveness and accuracy of the proposed method of long short-term memory neural network (LSTM) in predicting the foreign exchange market. The results from the proposed method will then be compared to the Multi-layered Perceptron neural network (MLP) and the Convolutional Neural Network (CNN) from other research papers. The project will be implemented using Keras neural libraries with Tensorflow as back end. The closing price of the USD/JPY, EUR/USD and GBP/USD will be used as the input to the LSTM model.
Schools: School of Electrical and Electronic Engineering 
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
Lee Xiang Wei FYP Report.pdf
  Restricted Access
3.48 MBAdobe PDFView/Open

Page view(s)

Updated on Sep 30, 2023

Download(s) 50

Updated on Sep 30, 2023

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.