{"paper_id":"2512.18918","title":"Needles in a haystack: using forensic network science to uncover insider trading","authors":["Gian Jaeger","Wang Ngai Yeung","Renaud Lambiotte"],"paper_date":"2025-12-21","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2512.18918v1","page_url":"https://thequant.space/flowcharts/needles-in-a-haystack-using-forensic-network-science-to-unc/","scores":{"empirical_rigor":8,"math_complexity":6,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a data‑driven network approach that flags groups of corporate insiders who report coordinated transactions indicative of insider trading.","quote":"we propose using a data-driven networks approach that flags groups of corporate insiders who report coordinated transactions that are indicative of insider trading.","summary":"Although the automation and digitisation of anti-financial crime investigation has made significant progress in recent years, detecting insider trading remains a unique challenge, partly due to the limited availability of labelled data. To address this challenge, we propose using a data-driven…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Legal trading windows are approximately 30 days per quarter.","type":"model","stated":"explicit","quote":"we chose 30 days with reference to research from Guay et al. (2021), who reported an average of 30-35 trading days for US companies."},{"assumption":"The synthetic calibrated null model preserves firm‑level temporal volume but destroys actor‑to‑actor synchronisation.","type":"model","stated":"explicit","quote":"This model preserves the exact temporal volume profile of the firm (including all bursts of activity potentially caused by exogenous factors) but destroys speciﬁc actor-to-actor synchronisation."},{"assumption":"Edge weights are based on same‑day or within‑week trade matches.","type":"statistical","stated":"explicit","quote":"Scombined = 1 if every trade has a same–day counterpart, and Scombined = 0 if no matches occur within a week."},{"assumption":"Insiders must report trades to the SEC within two working days via Form 4.","type":"market","stated":"explicit","quote":"legally requires that high‑ranking corporate insiders report purchasing or selling any financial security"},{"assumption":"The calibrated generative null model controls for trading windows, insider tenure, and firm lifespans.","type":"model","stated":"explicit","quote":"First, we use a calibrated generative model that controls for structural constraints such as trading windows, insider tenure, and firm lifespans."}]},"datasets":{"status":"available","items":[{"name":"SEC Form 4 insider trades (2014–2024)","provider":"U.S. Securities and Exchange Commission","kind":"alternative","access":"public","period":"2014-2024","universe":"U.S. corporate insiders (C‑suite, board members, major shareholders)","quote":"SEC by company insiders (C‑suite executives, board members and major shareholders) between 2014 and 2024."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"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":"unclear","findings":[{"finding":"Network metrics (e.g., number of nodes, edges, average degree) are far higher than those generated by both the structural and shuffled null models, indicating statistically significant coordination.","kind":"statistical","quote":"Global Connectivity Nodes 4,650 21.9 [15.0, 29.0] 1,075***"},{"finding":"Inspection of the empirical network uncovered two clusters of family members who consistently coordinate their trades.","kind":"other","quote":"which reveals interesting findings, including two clusters of family members who consistently coordinate their trades."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":15,"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":"2026-11-14T17:18:30Z"},"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/"}