Tools
Tools
Ifthikar, Syed (2018) Correlation Analysis and Prediction of Cryptocurrencies using Machine Learning. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (2MB) | Preview |
Abstract
Cryptocurrency prediction and price analysis has emerged one of the popular trends in the forecasting domain. Since the skyrocketing price rise of cryptocurrencies, the same time last year in December 2017, it has investors waiting for a right opportunity to invest in this new age digital money which is now a commodity. The aim of this project is to help investors with an understanding of a relationship between cryptocurrencies using the correlation coefficient analysis and predicting them using different data mining algorithm models. This project investigates different statistical correlation techniques as Spearman, Pearson and Kendall for the top five cryptocurrencies ranked as per their market capitalization. The project validates the performance of different machine learning algorithms using the RMSE error rate value. Seven different algorithms were used for the prediction models out of which LSTM had a good performance, whereas Random Forest did poorly amongst all cryptocurrencies. This project will help investors with better investment decisions for such volatile cryptocurrency markets and provide insights on cryptocurrency price movement directions as well as relativity between them.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | H Social Sciences > HA Statistics H Social Sciences > HF Commerce > Electronic Commerce T Technology > T Technology (General) > Information Technology |
| Divisions: | School of Computing > Master of Science in Data Analytics |
| Depositing User: | Dan English |
| Date Deposited: | 21 Jun 2021 12:53 |
| Last Modified: | 21 Jun 2021 14:12 |
| URI: | https://norma.ncirl.ie/id/eprint/4896 |
Actions (login required)
 |
View Item |