Prashant, Siddharth (2022) Bitcoin Price Prediction Using Time-series Analysis and Sentiment Analysis on Twitter Data in Cloud Environment. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (1MB) | Preview |
Abstract
The motivation of the project came due to the sudden surge in the prices of Cryptocurrencies, especially Bitcoin. Bitcoin is considered an investment asset. The price of Bitcoin is very fluctuating, volatile and depends on the Crypto-currency market and its demand. In this research, I have performed time-series based analysis and sentiment analysis based on the Twitter data to predict the price of bitcoin. For time-series analysis I have obtained better outcomes using Long short-term memory (LSTM). On the other hand, for the Twitter-based sentiment analysis method, the sentiments of tweets have been identified and based on the sentiment score the bitcoin price has been predicted. For Twitter-based sentiments Recurrent Neural Network (RNN) architecture has provided better outcomes in terms of Bitcoin price prediction. The model with minimum MSE (Mean Square Error) and MAE (Mean Absolute Error) score has been considered as the optimal model for predicting the price of bitcoin.
Item Type: | Thesis (Masters) |
---|---|
Subjects: | H Social Sciences > HF Commerce Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing H Social Sciences > HB Economic Theory > Business Cycles. Economic Fluctuations |
Divisions: | School of Computing > Master of Science in Cloud Computing |
Depositing User: | Tamara Malone |
Date Deposited: | 02 Dec 2022 16:47 |
Last Modified: | 06 Dec 2022 18:10 |
URI: | https://norma.ncirl.ie/id/eprint/5959 |
Actions (login required)
View Item |