{"paper_id":"2311.06292","title":"Towards a data-driven debt collection strategy based on an advanced machine learning framework","authors":["Abel Sancarlos","Edgar Bahilo","Pablo Mozo","Lukas Norman","Obaid Ur Rehma","Mihails Anufrijevs"],"paper_date":"2023-11-03","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2311.06292v1","page_url":"https://thequant.space/flowcharts/towards-a-data-driven-debt-collection-strategy-based-on-an-a/","scores":{"empirical_rigor":6.5,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a new machine learning modelling pipeline for estimating propensity to pay and expected cashflow in debt collection.","quote":"Specifically, a new machine learning modelling pipeline is presented showing how outperforms current strategies employed in the sector.","summary":"The European debt purchase market as measured by the total book value of purchased debt approached 25bn euros in 2020 and it was growing at double-digit rates. This is an example of how big the debt collection and debt purchase industry has grown and the important impact it has in the financial…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The market for debt purchase is large and growing at double‑digit rates.","type":"market","stated":"explicit","quote":"The European debt purchase market as measured by the total book value of purchased debt approached 25bn euros in 2020 and it was growing at double-digit rates."},{"assumption":"Propensity to pay can be estimated for each debtor for the next seven days.","type":"model","stated":"explicit","quote":"In particular, the goal is to estimate the propensity to pay in the next seven days at the beginning of each week."},{"assumption":"Strictly proper scoring rules (Brier and Logarithmic scores) provide reliable assessment of forecast quality.","type":"statistical","stated":"explicit","quote":"HPO job of the model generator in Section 3.1 is done in function of a strictly proper scoring rule."},{"assumption":"The proprietary dataset is representative of the debt collection industry.","type":"data","stated":"implied","quote":"The proposal in Section 3 is implemented on a proprietary dataset, generously provided by an important debt collection company."},{"assumption":"Calibration metrics (ECCE) are more reliable than traditional ECE metrics for model selection.","type":"statistical","stated":"explicit","quote":"we showed practically the better reliability of the latest ones to perform model selection."}]},"datasets":{"status":"available","items":[{"name":"Proprietary debt collection dataset","provider":"important debt collection company","kind":"other","access":"proprietary","period":"2022-08 to 2023-04","universe":"156 166 debtor‑level records","quote":"The data captures the time window from 2022-08 to 2023-04."}],"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":"The uncalibrated LightGBM model reduces error by 61% compared with Platt calibration and achieves a lower Logarithmic score.","kind":"performance","quote":"the uncalibrated model has an error reduction in 61% (with respect to Platt calibration) and not only that, but also a lower Logarithmic score."},{"finding":"ECE metrics can be misleading for calibration assessment, while ECCE metrics provide more stable model ranking across bin choices.","kind":"statistical","quote":"the unreliable ECE metrics can lead not only to select wrongly the best calibrated model but also to have potentially big mistakes"},{"finding":"Using ECCE‑R metric and Logarithmic score in the pipeline improves propensity‑to‑pay model selection and reduces over‑confidence.","kind":"predictive-accuracy","quote":"the pipeline workflow is designed to address the application specifications, taking into account several criteria considering strictly proper scoring rules (in particular, the Logarithmic score)"}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":16,"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":"2026-11-14T18:19:56Z"},"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/"}