Publicação
Cryptocurrency Price Prediction via Graph-Based Representations
| datacite.subject.fos | Ciências Naturais::Ciências da Computação e da Informação | pt_PT |
| dc.contributor.advisor | Santos, Augusto José Rabelo Almeida | |
| dc.contributor.author | Nwachukwu, Ebuka Collins | |
| dc.date.accessioned | 2025-11-12T11:20:52Z | |
| dc.date.available | 2025-11-12T11:20:52Z | |
| dc.date.issued | 2025-10-29 | |
| dc.description | Dissertation presented as the partial requirement for obtaining a Master's degree in Data Driven Marketing, specialization in Data Science for Marketing | pt_PT |
| dc.description.abstract | This study investigates the application of Graph Neural Networks (GNNs) for cryptocurrency price prediction by integrating structural relationships from both the digital asset market and traditional finance. Motivated by the growing body of research on spatio-temporal graph learning, this work explores how the quality and design of the input graph affect forecasting performance. Specifically, three graph structures are constructed: one based on Granger causality, another on the precision matrix via Graphical Lasso, and a third using mutual information. These graphs capture different perspectives on inter-asset relationships and are used as adjacency matrices in a hybrid deep learning framework combining 1D Convolutional Neural Networks (CNNs), Graph Convolutional Networks (GCNs), and Multi-Layer Perceptrons (MLPs). The model is trained on a dataset comprising daily closing prices of four cryptocurrencies—Bitcoin, Ethereum, Solana, and Tether along with the Financial Stress Index (FSI), spanning from October 1, 2019 to October 1, 2024 (1,534 days). Log returns are used for cryptocurrencies, and first differences for the FSI to enhance stationarity. Forecasts are generated for three time horizons: 1-day, 3-days, and 6-days ahead, using a 14-day input window in a sliding prediction framework. The results show that all three graph-based models perform well but exhibit different strengths across time horizons and assets. The mutual information-based model achieves the lowest average error for 1-day predictions (MAPE 1.8%), while the Granger causality model excels at 3-day forecasts (MAPE 2.7%), and the precision matrix model leads at 6-day horizons (MAPE 2.8%). Asset-wise, the Granger model produces the most accurate predictions for Bitcoin and Ethereum. These results outperform that of correlation based graphs from similar work by Patil (Patil et al., 2020) and it validates prior literature suggesting that financial graphs encode valuable relational information that can enhance predictive modelling. Although this work uses a small graph and shallow architecture, it demonstrates the potential of graph-based deep learning in financial forecasting. Future work could involve scaling to larger graphs with more assets and indicators, employing deeper or attention-based STGNN architectures, and experimenting with dynamic and weighted graphs to further exploit the rich structure of financial systems. | pt_PT |
| dc.identifier.tid | 204070546 | |
| dc.identifier.uri | http://hdl.handle.net/10362/190575 | |
| dc.language.iso | eng | pt_PT |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | pt_PT |
| dc.subject | Machine learning | pt_PT |
| dc.subject | Deep learning | pt_PT |
| dc.subject | Cryptocurrency | pt_PT |
| dc.subject | Graphical Neural Network | pt_PT |
| dc.subject | SDG 4 - Quality education | pt_PT |
| dc.subject | SDG 8 - Decent work and economic growth | pt_PT |
| dc.subject | SDG 9 - Industry, innovation and infrastructure | pt_PT |
| dc.title | Cryptocurrency Price Prediction via Graph-Based Representations | pt_PT |
| dc.type | master thesis | |
| dspace.entity.type | Publication | |
| rcaap.rights | openAccess | pt_PT |
| rcaap.type | masterThesis | pt_PT |
| thesis.degree.name | Mestrado em Marketing Analítico, especialização em Data Science for Marketing | pt_PT |