{"paper_id":"2610.07888","title":"A Functional Representation of Credit Behavior for Probability of Default Modeling","authors":["Jonas Brunholm","Bjarne Højgaard","Thomas D. Nielsen","Orimar Sauri"],"paper_date":"2026-10-06","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2610.07888","page_url":"https://thequant.space/flowcharts/a-functional-representation-of-credit-behavior-for-probability-of-default/","scores":{"empirical_rigor":8,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a functional data analysis framework with functional logistic regression for probability of default modeling.","quote":"This paper proposes a framework for modeling probability of default via functional data analysis.","summary":"This paper proposes a framework for modeling probability of default via functional data analysis. By representing a series of credit variables as functions, we investigate whether intra-monthly information improves default predictability in linear models. We further show how a range of widely used…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The binary response Y is modeled with a logistic link and functional predictors.","type":"model","stated":"explicit","quote":"We are interested in doing inference on the conditional probability π(X) := P(Y = 1|X), which is further assumed to satisfy η(X) := logit(π(X)) = α +"},{"assumption":"Functional predictors X_j(s) belong to the space of square‑integrable functions L2(T,ds).","type":"model","stated":"explicit","quote":"the components of the predictor X = (X1, . . . , Xd) : T →R^d are assumed to take values in the space of square integrable functions L2(T , ds)"},{"assumption":"Observations are an i.i.d. sample across borrowers.","type":"statistical","stated":"explicit","quote":"As in standard logistic regression, we suppose that the data forms an i.i.d. sample across i."},{"assumption":"Only borrowers with at least 12 months of post‑loan origination history are used.","type":"data","stated":"explicit","quote":"Note that the restriction of 12 months of loan history does not violate any regulatory requirements"},{"assumption":"The three underlying processes (account type, balance, credit limit) fully capture credit behavior variables.","type":"model","stated":"implied","quote":"we introduce a framework that represents a borrower through three continuous-time processes, account type, balance, and outstanding credit, from which the established credit behavior variables are constructed"}]},"datasets":{"status":"available","items":[{"name":"Nykredit borrower transaction snapshot","provider":"Nykredit","kind":"alternative","access":"proprietary","period":"2017-08-31 to 2019-12-31","universe":"129,789 unique borrowers (average 6 accounts, 5,255 transactions per borrower)","quote":"We use a snapshot of the data from 2017-08-31 until 2019-12-31, which consists of 129,789 unique borrowers as the basis of the analysis and subsequent modeling."},{"name":"Nykredit out‑of‑time (OOT) borrower dataset","provider":"Nykredit","kind":"alternative","access":"proprietary","period":"2021-01-31 to 2024-12-31","universe":"177,338 borrowers","quote":"we enrich the model evaluation with out-of-time (OOT) dataset from 2021-01-31 until 2024-12-31, consisting of 177,338 borrowers."}],"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":"forecast-accuracy","findings":[{"finding":"Functional logistic regression achieves the highest AUC (0.8996), outperforming standard logistic (0.8902) and XGBoost (0.8940).","kind":"performance","quote":"The functional logistic regression achieves the highest AUC (0.8996), ahead of the standard logistic regression (0.8902) by 0.94 percentage points and the XGBoost model (0.8940) by 0.56 percentage points."},{"finding":"In out‑of‑time testing, the functional model retains top rank and a significant AUC gain over standard logistic (0.0078, p<0.05).","kind":"statistical","quote":"The functional model exceeds the standard logistic regression by 0.0078 AUC, which is significant at the 5% level."},{"finding":"Functional logistic regression matches XGBoost performance while remaining a linear, interpretable model.","kind":"predictive-accuracy","quote":"the functional logistic regression had on-par performance with an XGBoost model, indicating that the performance gap between standard logistic regression and machine learning models can be closed by using a richer representation of the available data."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":23,"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":"2026-11-14T17:02:54Z"},"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/"}