Abstract

This thesis explores the application of Autoregressive Integrated Moving Average (ARIMA) model to predict Bitcoin prices, a prominent and volatile cryptocurrency. The research falls within the context of financial forecasting, focusing specifically on the cryptocurrency markets. The primary research question is: “Can time series analysis be used to predict the future price of Bitcoin?” To answer this question, historical Bitcoin daily price data from 17/09/2014 to 17/09/2023 was obtained from Kaggle and analyzed. The study employs ARIMA modeling techniques to capture the autocorrelation, seasonality, and trend present in Bitcoin price time series. As a prerequisite for ARIMA modeling, the data was transformed using a logarithmic function to stabilize the variance, then differenced by an order of 1 to make it stationary. The findings reveal that ARIMA can in fact predict Bitcoin prices. The best model in terms of lowest error rate is ARIMA(4,1,1), which achieved an RMSE of 0.03099 and MAE of 0.02121. However, the lowest MAPE that could be achieved using historical data alone was 123%. This indicates that traditional time series techniques are limited by their use of only past values to predict future ones, especially considering that cryptocurrency prices are influenced by various other features and external factors. Future research should explore correlations of Bitcoin with other currencies, include additional factors, and investigate hybrid models like ARIMA with CNN or LSTM for improved predictions.

Library of Congress Subject Headings

Bitcoin--Forecasting; Time-series analysis

Publication Date

2-2024

Document Type

Thesis

Student Type

Graduate

Degree Name

Professional Studies (MS)

Department, Program, or Center

Graduate Programs & Research

Advisor

Sanjay Modak

Advisor/Committee Member

Ionnis Karamitsos

Campus

RIT Dubai

Plan Codes

PROFST-MS

Download

Share

COinS