CryptoGAT: Are Time Series Models Effective for Cryptocurrency Forecasting?

By Yu Peng, Matloob Khushi, Josiah Poon

Published 2026-06-26

Everscope rating

1162.6

Relevance to quantitative trading

9 / 10

Implementation complexity

3 / 10

Reproducibility

4 / 5

About this paper

Methodology: CryptoGAT (Graph Attention Network for Cryptocurrency Prediction). Problem types: Time Series Forecasting, Graph Learning, Regression, Portfolio Optimization.

arXiv:2606.27670 · Code · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.