Predicting Terrorism Attacks with Bitcoin Price Fluctuations using Machine Learning.

Shah, Nisarg (2020) Predicting Terrorism Attacks with Bitcoin Price Fluctuations using Machine Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

The price variances in bitcoin has aroused the enthusiasm of numerous individuals towards it as a methods for fast increases, regardless of whether they are the deceitful components of the general public, for example, lawbreakers and terrorists. Terrorists have huge measure of money or assets which they can use in the fluctuating business sector of bitcoin to utilize strategies like pump and dump to rapidly build their additions and use them for subsidizing of their exercises. ISIS is known for using Bitcoin as a method of accepting donations.
Objective: Does ISIS use pump and dump method to manipulate the Bitcoin prices. Do they do this when there is a terror attack in countries where ISIS is active.
Dataset: A publicly available dataset Global Terrorism Database maintained by Maryland State University has been used along with Bitcoin Price from Bitstamp Cryptocurrency exchange is used which is available on Kaggle.
Methodology: ARIMA, RNN and LSTM have been used to find the Bitcoin Price Prediction. ARIMA is used to find the number of people killed in Terror attacks. Patterns in
fluctuations of price and terrorist attacks are found when all the data is visualized in Tableau.
Results: ARIMA had an Mean Absolute Percentage Error (MAPE) of 8% RNN had an MAPE of 6% and LSTM had the lowest MAPE of 3% for predicting Bitcoin price. Terrorism prediction had an MAPE of 33% using ARIMA.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software H Social Sciences > HF Commerce > Electronic Commerce
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	16 Jun 2020 10:26
Last Modified:	16 Jun 2020 10:26
URI:	https://norma.ncirl.ie/id/eprint/4291

Actions (login required)

View Item