This dissertation was written as a part of the MSc in Data Science at the International
Hellenic University.
The main goal of this project is the prediction of Bitcoin price and movement using advanced machine learning techniques. Financial and blockchain features were used to
train our algorithms and discover insights and patterns that describe Bitcoin movements
during time. Furthermore, a sentiment analysis was deployed so to identify how news
affect bitcoin price movement. Twitter posts were collected through Twitter search API
with Tweepy open source library assistance. Python is the programming language that
was used to fulfil the dissertation’s coding part.
Machine learning algorithms such as Support Vector Machines, Extra trees, Gradient
Boosting and Neural Networks were deployed to tackle our main problem.
Collections
Show Collections