Graph-based spatio-temporal models built from aggregated crypto market data detect pump-and-dump schemes more effectively than standard machine learning baselines.
Discrete graph structure learning for forecasting multiple time series,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fraud Detection in Cryptocurrency Markets with Spatio-Temporal Graph Neural Networks
Graph-based spatio-temporal models built from aggregated crypto market data detect pump-and-dump schemes more effectively than standard machine learning baselines.