Open AccessRegression based Analysis for Bitcoin Price Prediction
Author(s) -
Azim Muhammad Fahmi,
Noor Azah Samsudin,
Aida Mustapha,
Nazim Razali,
Shamsul Kamal Ahmad Khalid
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i4.38.27642
Subject(s) - decision tree , econometrics , regression , linear regression , regression analysis , liberian dollar , economics , us dollar , cryptocurrency , artificial neural network , bayesian multivariate linear regression , computer science , statistics , artificial intelligence , machine learning , currency , monetary economics , mathematics , finance , computer security
In 2017, a significant number of individuals profited from the staggering growth of the price of Bitcoin from $800 USD in January to almost $20,000 USD in December. Because the cryptocurrency market being relatively new when compared to traditional markets such as stocks, foreign exchange, and gold, there is a significant lack of studies in regard to predicting its price behavior. This research is interested in evaluating a number of regression-based algorithms in predicting the price of the Bitcoin (BTC) against United States Dollar (USD). Among the algorithms that will be investigated include the Linear Regression (LR), Neural Network Regression (NNR), Bayesian Linear Regression (BLR), and Boosted Decision Tree Regression (BDTR). By applying such regression-based analysis algorithms, the findings f should further help document the behavior of such a brand new, challenging yet extremely lucrative market.