{"paper_id":"2507.08835","title":"Representation learning with a transformer by contrastive learning for money laundering detection","authors":["Harold Guéneau","Alain Celisse","Pascal Delange"],"paper_date":"2025-07-07","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2507.08835v1","page_url":"https://thequant.space/flowcharts/representation-learning-with-a-transformer-by-contrastive-le/","scores":{"empirical_rigor":4,"math_complexity":6.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes a two‑step methodology: a transformer pretrained by contrastive learning on raw transaction time series, followed by a two‑threshold classification calibrated with the Benjamini‑Hochberg procedure to control false positives.","quote":"... learning representations of time series through contrastive learning (without any labels). The second step leverages these representations to generate a money laundering scoring of all observations. A two‑thresholds approach is t","summary":"The present work tackles the money laundering detection problem. A new procedure is introduced which exploits structured time series of both qualitative and quantitative data by means of a transformer neural network. The first step of this procedure aims at learning representations of time series…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The dataset is strongly imbalanced with a very low proportion of fraudsters.","type":"data","stated":"explicit","quote":"One important specificity of our dataset is its strong imbalance regarding the (expected) very low proportion of fraudsters among all observations."},{"assumption":"Gaussian noise added in latent space is small enough to preserve the local structure of the data.","type":"model","stated":"explicit","quote":"This mechanism helps in creating ’new observations’ from the original ones by Gaussian perturbation [DT17], which yields realistic observations provided σ²"},{"assumption":"Descriptors of normal time series do not vary over time, allowing train/test split by disjoint periods.","type":"data","stated":"explicit","quote":"Assuming that the relevant descriptors of normal time series (as opposed to time series of abnormal accounts) should not vary along the time, the training and test sets have been created by considering two disjoint time periods."},{"assumption":"Anonymization via differential privacy with ε=1 preserves enough information for modeling.","type":"data","stated":"explicit","quote":"For this procedure, the privacy parameter ϵ is equal to 1. After such an anonymization process, the data only reflect the generic financial activity of a set of accounts..."},{"assumption":"The transformer can learn useful representations without any labeled data.","type":"model","stated":"explicit","quote":"... stems from the use of contrastive learning for (pre‑)training the transformer without labeled data."},{"assumption":"The two‑threshold BH calibration effectively controls the false discovery rate.","type":"statistical","stated":"explicit","quote":"These two thresholds are calibrated by means of the Benjamini‑Hochberg multiple testing procedure, which allows for controlling the False Discovery rate (FDR) criterion and therefore avoids too many false positives."}]},"datasets":{"status":"available","items":[{"name":"time-series-of-transactions-money-laundering","provider":"Kaggle","kind":"alternative","access":"public","period":"3 months","universe":"companies from various industrial domains","quote":"The dataset has been made freely available on Kaggle dataset: https://www.kaggle.com/datasets/haroldg/time-series-of-transactions-money-laundering/ data","known_id":"kaggle"}],"known":[{"id":"kaggle","name":"Kaggle","provider":"Kaggle","kind":"other","access":"public","quote":"The dataset has been made freely available on Kaggle dataset: https: // www. kaggle. com/ datasets/ haroldg/ time-series-of-transactions-money-laundering/ data Confidentiality In order to protect the confidentiality of users, the data have been anonymized using differential privacy techniques combined with a PCA transformation [IS16, HBMAL19].","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"unclear"},"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":"The transformer‑based procedure reduces false positives dramatically compared to rule‑based strategies while maintaining detection of both fraudsters and non‑fraudsters.","kind":"performance","quote":"It also illustrates the higher ability of the new procedure for detecting non‑fraudsters as well as fraudsters, while keeping the false positive rate under control. This greatly contrasts with rule‑based procedures..."},{"finding":"Experimental results on real‑life data show a consistent behavior and a large reduction in false positives relative to rule‑based systems.","kind":"performance","quote":"Despite this limitation, the reported empirical results demonstrate a consistent behavior, reducing a lot the number of false positives compared to rule‑based strategies."},{"finding":"The approach suggests even better results could be achieved on larger datasets.","kind":"other","quote":"All of this even suggests better results on larger datasets."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":27,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"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":"2026-11-14T17:33:48Z"},"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/"}