Predicting foreign currency exchange trends using neural networks | |
| Author | Nan Thu Zar Aung |
| Subject(s) | Neural networks (Computer science) Foreign exchange rates-Mathematical models Data mining-Data processing |
| Note | A research study submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Computer Science |
| Publisher | Asian Institute of Technology |
| Abstract | The purpose of this research study is to make the prediction of the trends (up, equal or down) the two foreign currency exchange (United States Dollar and European Euro) rate using the neural network algorithms. This study will help the local businessmen to be encouraged and invested on their start-up and existing business. The historical value of foreign currency exchange rate was downloaded from www.investing.com. Data Transformation was needed in this research study. The close price is a continuous so that it was transformed to binary value to predict the forex trends. After changing binary value, four training models (each dataset) which were: (1) Training Model using (50%) odd day of datasets without yesterday’s close trend, (2) Training Model using (50%) odd day of datasets with yesterday’s close trend, (3) Training Model using first five years of datasets without yesterday’s close trend and (4) Training Model using first five years of datasets with yesterday’s close trend were used to train the model to determine which model is the best in terms of accuracy percentage. Among those four training models (each dataset), the training model using first five years of datasets without yesterday’s close trend is best model with highest accuracy percentage and then it is chosen to further analysis. When testing datasets were used for testing model to predict the next day’s close trend, these results illustrated that both testing models are predicted “Down” which means that the next day’s close price(1st November, 2019) will be lower than the current day(today). This research study is proved by comparing between this research study’s result and actual historical value. |
| Year | 2020 |
| Type | Research Study Project Report (RSPR) |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Science (CS) |
| Chairperson(s) | Chutiporn Anutariya; |
| Examination Committee(s) | Vatcharaporn Esichaikul;Nicole, Olivier Christian; |
| Scholarship Donor(s) | AIT Fellowship; |
| Degree | Research Studies Project Report (M. Eng.) - Asian Institute of Technology, 2020 |