{"paper_id":"2306.16424","title":"Realistic Synthetic Financial Transactions for Anti-Money Laundering Models","authors":["Erik Altman","Jovan Blanuša","Luc von Niederhäusern","Béni Egressy","Andreea Anghel","Kubilay Atasu"],"paper_date":"2023-06-22","paper_type":"dataset-benchmark","paper_url":"https://arxiv.org/pdf/2306.16424v3","page_url":"https://thequant.space/flowcharts/realistic-synthetic-financial-transactions-for-anti-money-la/","scores":{"empirical_rigor":6,"math_complexity":4.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a synthetic financial transaction generator and a set of realistic, standardized AML datasets for benchmarking anti‑money‑laundering models.","quote":"A synthetic financial transaction generator, which builds a multi-agent virtual world in which some of the agents are criminals with illicit income to launder","summary":"With the widespread digitization of finance and the increasing popularity of cryptocurrencies, the sophistication of fraud schemes devised by cybercriminals is growing. Money laundering – the movement of illicit funds to conceal their origins – can cross bank and national boundaries, producing…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The synthetic generator is calibrated to match real transactions as closely as possible.","type":"model","stated":"explicit","quote":"We have calibrated this agent-based generator to match real transactions as closely as possible and made the datasets public."},{"assumption":"The generator knows the source of all funds, providing perfect labeling of laundering transactions.","type":"data","stated":"explicit","quote":"Since the generator knows the source of all funds, it knows which transfers are laundering."},{"assumption":"The generated AML datasets are highly imbalanced between laundering and non‑laundering transactions.","type":"data","stated":"implied","quote":"As our proposed datasets are naturally very imbalanced, traditional metrics like accuracy do not provide a reliable measure of model performance."},{"assumption":"Criminal agents launder less frequently in low‑illicit (LI) datasets, making pattern discovery harder.","type":"model","stated":"explicit","quote":"The primary difference between LI and HI datasets is that criminals launder less frequently in LI, which makes it harder to discover the laundering patterns."},{"assumption":"Weighting the minority class higher in the loss function improves performance on LI datasets.","type":"model","stated":"explicit","quote":"To address this, our models incorporate the measure of weighting the predictions of the minority class higher in the loss function."}]},"datasets":{"status":"available","items":[{"name":"AMLworld synthetic AML datasets","provider":"Kaggle","kind":"synthetic","access":"public","period":null,"universe":null,"quote":"Six AMLworld datasets are now publicly available on Kaggle [50].","known_id":"kaggle"}],"known":[{"id":"kaggle","name":"Kaggle","provider":"Kaggle","kind":"other","access":"public","quote":"3.5 Public Availability of Synthetic Data We have used AMLworld to create several synthetic AML datasets that have been made available on Kaggle [50].","mentions":2,"used_in":2}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"synthetic"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"Message‑passing GNNs that exploit account connectivity capture laundering transactions effectively, with advanced architectures (PNA, GIN+EU) significantly enhancing performance.","kind":"performance","quote":"These results show that message-passing GNNs that exploit the connectivity between accounts are effective in capturing laundering transactions. Advanced GNN architectures such as PNA and GIN+EU, which respectively implement extended message aggregation and edge update mechanisms, significantly enhance the GNN performan"},{"finding":"Pre‑training on higher‑illicit (HI) datasets and fine‑tuning improves F1 on lower‑illicit (LI) datasets, e.g., PNA fine‑tuned reaches 27.38 % F1 on LI‑Small.","kind":"performance","quote":"... performance on LI data can be improved further for the LI‑Small dataset, where directly using the models trained on HI datasets is ineffective, by fine-tuning the HI PNA models using the LI dataset."},{"finding":"GBT baselines achieve competitive results, with near‑par performance to PNA despite lacking handcrafted features.","kind":"performance","quote":"An interesting observation is the near-par performance of PNA with GBT baselines, even without relying on handcrafted features."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":13,"citations":{"cited_by_in_corpus":2,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":0},"independent_papers":[{"paper":{"paper_id":"2411.05815","title":"Graph Neural Networks for Financial Fraud Detection: A Review","paper_date":"2024-11-01","authors":["Dawei Cheng","Yao Zou","Sheng Xiang","Changjun Jiang"],"empirical_rigor":2,"page_url":"https://thequant.space/flowcharts/graph-neural-networks-for-financial-fraud-detection-a-revie/"},"how":"uses_method_or_data","quote":null}],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T18:25:29Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}