{"paper_id":"2601.07588","title":"Temporal-Aligned Meta-Learning for Risk Management: A Stacking Approach for Multi-Source Credit Scoring","authors":["O. Didkovskyi","A. Vidali","N. Jean","G. Le Pera"],"paper_date":"2026-01-12","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2601.07588v1","page_url":"https://thequant.space/flowcharts/temporal-aligned-meta-learning-for-risk-management-a-stacki/","scores":{"empirical_rigor":7,"math_complexity":3.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a two-step meta‑learning framework that first estimates annual PDs with a static model and then models monthly PD evolution with a dynamic model, using stacking to combine multiple scoring systems.","quote":"Thus we propose a two-step framework that explicitly models the temporal gap between data reference dates and evaluation dates.","summary":"This paper presents a meta-learning framework for credit risk assessment of Italian Small and Medium Enterprises (SMEs) that explicitly addresses the temporal misalignment of credit scoring models. The approach aligns financial statement reference dates with evaluation dates, mitigating bias…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The dynamic model assumes smooth risk evolution between balance‑sheet assessments.","type":"model","stated":"explicit","quote":"The dynamic model assumes smooth risk evolution between balance sheet assessments."},{"assumption":"Balance‑sheet data become available 3‑9 months after the reference date, creating a lag that must be accounted for.","type":"data","stated":"explicit","quote":"Balance sheets for December 31st become available 3-9 months later; CR data has a 2-month lag; internal data provides near real-time updates."},{"assumption":"Point‑in‑time consistency can be achieved by aligning the latest available information to the reference period being modeled.","type":"data","stated":"explicit","quote":"To address temporal misalignment we introduce point-in-time consistency: identifying the latest information related to the reference period being modeled."},{"assumption":"Logistic regression as meta‑learner preserves interpretability while allowing integration of new indicators without retraining base models.","type":"model","stated":"explicit","quote":"We employ logistic regression as the meta-learner, treating base-model PD outputs as learned representations encoding distinct temporal views of risk."}]},"datasets":{"status":"available","items":[{"name":"Balance Sheets","provider":"illimity bank","kind":"fundamentals","access":"proprietary","period":"2017-2023","universe":"Italian SMEs in illimity portfolio","quote":"Balance Sheets 2017-2023 Annual 18,454 3-9 months"},{"name":"Central Credit Register","provider":"Central Credit Register","kind":"alternative","access":"proprietary","period":"2017-2024","universe":"Italian SMEs in illimity portfolio","quote":"Central Credit Register 2017-2024 Monthly 18,454 2 months"},{"name":"Expert Indicators","provider":null,"kind":"alternative","access":"proprietary","period":"2017-2024","universe":"Italian SMEs in illimity portfolio","quote":"Expert Indicators 2017-2024 Variable 18,454 2 months"}],"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 static fusion model achieves an AUC of 0.900, outperforming the CRD baseline (0.833) and the behavioral baseline (0.808).","kind":"predictive-accuracy","quote":"The Static Fusion model achieves AUC=0.900, outperforming CRD (0.833) and BHV (0.808) baselines."},{"finding":"The dynamic model shows strong performance across horizons, with Quadratic Weighted Kappa ranging from 0.772 (6‑month ahead) to 0.951 (12‑month ahead).","kind":"predictive-accuracy","quote":"The dynamic model maintains strong performance across temporal horizons (Table 7), with QWK ranging from 0.772 (6-month ahead) to 0.951 (12-month ahead)."},{"finding":"Performance gains are especially pronounced for medium and large enterprises, with AUCs of 0.882 and 0.871 respectively.","kind":"performance","quote":"The model demonstrates robust performance across different company size segments, with particularly strong results for medium and large enterprises as shown in Table 6."}],"reported_performance":null,"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":22,"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":"2026-11-14T17:16:11Z"},"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/"}