{"paper_id":"2410.22519","title":"Evaluating utility in synthetic banking microdata applications","authors":["Hugo E. Caceres","Ben Moews"],"paper_date":"2024-10-29","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2410.22519v1","page_url":"https://thequant.space/flowcharts/evaluating-utility-in-synthetic-banking-microdata-applicatio/","scores":{"empirical_rigor":6,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a utility‑and‑privacy framework for synthetic banking microdata and provides the first synthetic datasets for financial usage indices, term deposit yield curves, and credit card transition matrices.","quote":"We develop a framework that considers the utility and privacy requirements of regulators, and apply this to financial usage indices, term deposit yield curves, and credit card transition matrices.","summary":"Financial regulators such as central banks collect vast amounts of data, but access to the resulting fine-grained banking microdata is severely restricted by banking secrecy laws. Recent developments have resulted in mechanisms that generate faithful synthetic data, but current evaluation…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Inputs to the marginal‑based inference mechanisms must be categorical.","type":"data","stated":"explicit","quote":"As they use discrete marginals, inputs are required to be categorical."},{"assumption":"Differential privacy noise is added according to the specified DP parameters (σ, ε, δ).","type":"statistical","stated":"explicit","quote":"The mechanism then calculates the amount of noise that should be added to the sensitive dataset to satisfy the criteria, using the differential privacy parameters as σ = …"},{"assumption":"Numeric features are discretised via k‑means clustering before synthetic generation.","type":"model","stated":"explicit","quote":"In the data-driven PS, we discretise numeric features through k-means transformations, as credit management actions such as selling non‑performing loans result in non‑normal and multi‑modal distributions."},{"assumption":"Synthetic information products require fewer resources than maintaining integrated data portals.","type":"other","stated":"implied","quote":"resources required to implement synthetic information products can be lower than maintaining integrated data portals or processing individual information requests."},{"assumption":"Pre‑processing strategies (CBP vs data‑driven) affect utility and error propagation.","type":"model","stated":"implied","quote":"We also assess two separate pre‑processing strategies, one following the CBP’s current data definitions and one data‑driven."}]},"datasets":{"status":"available","items":[{"name":"Central Bank of Paraguay banking microdata (synthetic)","provider":"Central Bank of Paraguay","kind":"synthetic","access":"public","period":null,"universe":"approximately 3.7 million individuals, 13,000 term deposits, 700,000 credit cards","quote":"Our financial inclusion, term yield curve, and credit risk domain applications cover approximately 3.7 million unique individuals, 13,000 term deposits, and 700,000 credit cards, respectively."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"weekly-monthly"},"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":"Applications based on frequency tables are especially suitable for synthetic data, and marginal‑based inference mechanisms outperform GAN models for these tabular tasks.","kind":"performance","quote":"We find that applications less susceptible to post‑processing information loss, which are based on frequency tables, are particularly suited for this approach, and that marginal‑based inference mechanisms to outperform generative adversarial network models for these applications."},{"finding":"Synthetic microdata yields relatively high error on weighted average interest and total capital (1%‑10% error and large absolute deviations).","kind":"statistical","quote":"Here, all mechanisms average relatively high error with regard to the original WAI and TC domain (1% - 10% and 47 billion PYG, respectively)."},{"finding":"Utility metrics should be evaluated at the intended granularity because errors are unevenly distributed across granularity levels.","kind":"theoretical","quote":"We find that utility metrics for domain applications should be evaluated at their intended granularity, as errors may be distributed unevenly between granularity levels."},{"finding":"Synthetic data can provide new granular information products, such as credit‑card loss data not currently disclosed.","kind":"other","quote":"For example, the loss data for credit cards is information not currently featured and valuable to financial institutions, researchers, and practitioners."},{"finding":"Regulators with limited experience and resources may encounter additional challenges when adopting synthetic data generation.","kind":"other","quote":"Our data extraction, validation, and processing indicate that regulators with less experience and resources are likely to face additional challenges."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":25,"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":"2026-11-14T17:57:34Z"},"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/"}