Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Exploring the ethereum dataset with the aim of price trend prediction using the recurrent neutral network, LSTM, gated recurrent unit and an ensemble algorithm in combination with X data
Thesis (MA)--Stellenbosch University, 2025.
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | en_ZA |
| Published: |
Stellenbosch : Stellenbosch University
2025
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867613895985725440 |
|---|---|
| access_status_str | Open Access |
| author | Van Wyk, Chad |
| author2 | Blaauw, Dewald N. |
| author_browse | Blaauw, Dewald N. Van Wyk, Chad |
| author_facet | Blaauw, Dewald N. Van Wyk, Chad |
| author_sort | Van Wyk, Chad |
| collection | Thesis |
| dc_rights_str_mv | Stellenbosch University |
| description |
Thesis (MA)--Stellenbosch University, 2025. |
| format | Thesis |
| id | oai:scholar.sun.ac.za:10019.1/132292 |
| institution | Stellenbosch University (South Africa) |
| language | en_ZA |
| last_indexed | 2026-06-10T12:43:25.190Z |
| license_str | Other — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from SUNScholar — Stellenbosch University Repository |
| publishDate | 2025 |
| publishDateRange | 2025 |
| publishDateSort | 2025 |
| publisher | Stellenbosch : Stellenbosch University |
| publisherStr | Stellenbosch : Stellenbosch University |
| record_format | dspace |
| source_str | SUNScholar — Stellenbosch University Repository |
| spelling | oai:scholar.sun.ac.za:10019.1/132292 Exploring the ethereum dataset with the aim of price trend prediction using the recurrent neutral network, LSTM, gated recurrent unit and an ensemble algorithm in combination with X data Van Wyk, Chad Blaauw, Dewald N. Stellenbosch University. Faculty of Arts and Social Sciences. Dept. of Information Science. machine learning -- Finance Cryptocurrencies Digital currency UCTD Thesis (MA)--Stellenbosch University, 2025. van Wyk, C. 2025. Exploring the Ethereum dataset with the aim of Price Trend Prediction Using the Recurrent Neutral Network, LSTM, Gated Recurrent Unit and an ensemble algorithm in combination with X data. Unpublished masters thesis. Stellenbosch: Stellenbosch University [online]. Available: https://scholar.sun.ac.za/items/5cdca44f-2038-43b1-8edf-3642d7961bb6 This study investigates the application of machine learning techniques and sentiment analysis for predicting cryptocurrency market price movements. Cryptocurrency markets have gained immense traction in the financial sector and continue to grow exponentially, with the introduction of an array of new stable and alternative coins. Attempting to understand the market dynamics has, therefore, evolved into a domain of interest for many academic researchers and professionals. While prior research has primarily placed focus on Bitcoin, this study attempts to extend these approaches to the Ethereum cryptocurrency market by employing a variety of price prediction techniques as well as incorporate social media sentiment data, to deduce whether the influence of the public’s opinion has a strong enough prediction influence on the overall price movement. The research compares the performance of Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and an ensemble algorithm which combines these approaches. Additionally, the study explores the impact of public sentiment on Ethereum price movements by utilising tweet elements from the X platform as a secondary feature input. Both base and bivariate models are implemented, with the latter model incorporating Ethereum market and sentiment analysis data as input. Results exhibit the viability of predicting cryptocurrency market trends applying the aforementioned machine learning techniques. The inclusion of the social media sentiment as an additional feature in modified base models did not, however, consistently enhance the overall accuracy or performance metrics of the bivariate predictive models. This study contributes to the developing body of literature on cryptocurrency market prediction and offers insights into the complex correlation between public sentiment and market behaviour in the context of Ethereum. Masters 2025-06-03T05:33:45Z 2025-06-03T05:33:45Z 2025-03 Thesis https://scholar.sun.ac.za/handle/10019.1/132292 en_ZA Stellenbosch University xvi, 146 pages : illustrations application/pdf Stellenbosch : Stellenbosch University |
| spellingShingle | machine learning -- Finance Cryptocurrencies Digital currency UCTD Van Wyk, Chad Exploring the ethereum dataset with the aim of price trend prediction using the recurrent neutral network, LSTM, gated recurrent unit and an ensemble algorithm in combination with X data |
| title | Exploring the ethereum dataset with the aim of price trend prediction using the recurrent neutral network, LSTM, gated recurrent unit and an ensemble algorithm in combination with X data |
| title_full | Exploring the ethereum dataset with the aim of price trend prediction using the recurrent neutral network, LSTM, gated recurrent unit and an ensemble algorithm in combination with X data |
| title_fullStr | Exploring the ethereum dataset with the aim of price trend prediction using the recurrent neutral network, LSTM, gated recurrent unit and an ensemble algorithm in combination with X data |
| title_full_unstemmed | Exploring the ethereum dataset with the aim of price trend prediction using the recurrent neutral network, LSTM, gated recurrent unit and an ensemble algorithm in combination with X data |
| title_short | Exploring the ethereum dataset with the aim of price trend prediction using the recurrent neutral network, LSTM, gated recurrent unit and an ensemble algorithm in combination with X data |
| title_sort | exploring the ethereum dataset with the aim of price trend prediction using the recurrent neutral network lstm gated recurrent unit and an ensemble algorithm in combination with x data |
| topic | machine learning -- Finance Cryptocurrencies Digital currency UCTD |
| url | https://scholar.sun.ac.za/handle/10019.1/132292 |
| work_keys_str_mv | AT vanwykchad exploringtheethereumdatasetwiththeaimofpricetrendpredictionusingtherecurrentneutralnetworklstmgatedrecurrentunitandanensemblealgorithmincombinationwithxdata |