Open AccessEnsemble Method for Forex Rate Prediction using OHLC Data
Author(s) -
Srijan Kumar Upadhyay
Publication year - 2021
Publication title -
international journal for research in applied science and engineering technology
Language(s) - English
Resource type - Journals
ISSN - 2321-9653
DOI - 10.22214/ijraset.2021.35328
Subject(s) - computer science , exchange rate , foreign exchange market , support vector machine , artificial neural network , task (project management) , process (computing) , artificial intelligence , regression , ensemble forecasting , econometrics , machine learning , data mining , statistics , finance , economics , mathematics , operating system , management
Forex rate is a crucial indicator of the economic health of the country. Accurate prediction of forex rates thus becomes essential to take necessary steps to ensure the sound economic health of its citizens. Due to the chaotic and nonsta-tionary nature of the data, its prediction becomes a complicated task. Through the results obtained from various researches, it becomes evident that hybrid models have outperformed individual base learners in resembling the actual data generation process and forecasting future data. In this paper,an ensemble-based approach is adopted to enhance forecasting accuracy. The model is trained on the OHLC data (high, low, open, and close) of the previous day for enhanced exchange rate prediction of USD compared to different currencies. This paper applies a hybrid model of Convolution Neural Network ,Long Short Term Network and Support Vector Regression trained on the previous peak data. Results obtained after experiments indicate that a hybrid model improved the prediction accuracy when compared to individual models.