{"ID":2864203,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.23712","arxiv_id":"2509.23712","title":"FraudTransformer: Time-Aware GPT for Transaction Fraud Detection","abstract":"Detecting payment fraud in real-world banking streams requires models that can exploit both the order of events and the irregular time gaps between them. We introduce FraudTransformer, a sequence model that augments a vanilla GPT-style architecture with (i) a dedicated time encoder that embeds either absolute timestamps or inter-event values, and (ii) a learned positional encoder that preserves relative order. Experiments on a large industrial dataset -- tens of millions of transactions and auxiliary events -- show that FraudTransformer surpasses four strong classical baselines (Logistic Regression, XGBoost and LightGBM) as well as transformer ablations that omit either the time or positional component. On the held-out test set it delivers the highest AUROC and PRAUC.","short_abstract":"Detecting payment fraud in real-world banking streams requires models that can exploit both the order of events and the irregular time gaps between them. We introduce FraudTransformer, a sequence model that augments a vanilla GPT-style architecture with (i) a dedicated time encoder that embeds either absolute timestamp...","url_abs":"https://arxiv.org/abs/2509.23712","url_pdf":"https://arxiv.org/pdf/2509.23712v2","authors":"[\"Gholamali Aminian\",\"Andrew Elliott\",\"Tiger Li\",\"Timothy Cheuk Hin Wong\",\"Victor Claude Dehon\",\"Lukasz Szpruch\",\"Carsten Maple\",\"Christopher Read\",\"Martin Brown\",\"Gesine Reinert\",\"Mo Mamouei\"]","published":"2025-09-28T07:53:41Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"stat.ML\"]","methods":"[\"Transformer\"]","has_code":false}