A contrastively pre-trained transformer on raw transaction time series is reported to improve money-laundering detection and FDR control over tabular and LSTM baselines, though the evaluation protocol limits the strength of the claim.
The control of the false discovery rate in multiple testing under dependency
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Representation learning with a transformer by contrastive learning for money laundering detection
A contrastively pre-trained transformer on raw transaction time series is reported to improve money-laundering detection and FDR control over tabular and LSTM baselines, though the evaluation protocol limits the strength of the claim.