{"paper_id":"2512.12783","title":"Credit Risk Estimation with Non-Financial Features: Evidence from a Synthetic Istanbul Dataset","authors":["Atalay Denknalbant","Emre Sezdi","Zeki Furkan Kutlu","Polat Goktas"],"paper_date":"2025-12-14","paper_type":"dataset-benchmark","paper_url":"https://arxiv.org/pdf/2512.12783v2","page_url":"https://thequant.space/flowcharts/credit-risk-estimation-with-non-financial-features-evidence/","scores":{"empirical_rigor":7,"math_complexity":2,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes an open synthetic Istanbul 2025 Q1 dataset and a fully reproducible modeling pipeline that uses alternative behavioural attributes for credit scoring.","quote":"We contribute an open Istanbul 2025 Q1 synthetic dataset, a fully reproducible modeling pipeline, and empirical evidence that a concise set of behavioural attributes can approach bureau level discrimination power while serving borrowers who lack formal credit records.","summary":"Financial exclusion constrains entrepreneurship, increases income volatility, and widens wealth gaps. Underbanked consumers in Istanbul often have no bureau file because their earnings and payments flow through informal channels. To study how such borrowers can be evaluated we create a synthetic…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The synthetic dataset accurately reproduces the 2025 Q1 TÜİK census marginals and telecom usage patterns of Istanbul residents.","type":"data","stated":"explicit","quote":"synthetic dataset of one hundred thousand Istanbul residents that reproduces first quarter 2025 TÜİK (TURKSTAT) census marginals and telecom usage patterns."},{"assumption":"Alternative behavioural attributes are available and can be collected quickly with informed consent.","type":"execution","stated":"implied","quote":"From an operational standpoint lenders must ask whether the data needed for the Full model can be gathered quickly and with informed consent."},{"assumption":"Five‑fold stratified validation provides a reliable estimate of model performance.","type":"statistical","stated":"implied","quote":"Across five fold stratified validation the alternative block raises area under the ROC curve by about 1.3 percentage points and lifts balanced F1 from roughly 0.84 to 0.95."}]},"datasets":{"status":"available","items":[{"name":"Istanbul 2025 Q1 synthetic dataset","provider":null,"kind":"synthetic","access":"public","period":"2025 Q1","universe":"one hundred thousand Istanbul residents","quote":"synthetic dataset of one hundred thousand Istanbul residents that reproduces first quarter 2025 TÜİK (TURKSTAT) census marginals and telecom usage patterns."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"synthetic"},"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":"Adding ten alternative attributes raises AUC by about 0.013 (1.3 percentage points) and improves balanced F1 from roughly 0.84 to 0.95, a 14% gain.","kind":"predictive-accuracy","quote":"Across five fold stratified validation, the alternative block raises area under the ROC curve by about 1.3 percentage points and lifts balanced F1 from roughly 0.84 to 0.95, a 14 percent gain."},{"finding":"CatBoost Full flags 96 of 100 defaulters while issuing fewer than five false approvals, outperforming demographic‑only models.","kind":"performance","quote":"CatBoost Full, for example, flags ninety six of one hundred defaulters while issuing fewer than five false approvals in the same batch, a separation level that pure demographic scorecards cannot reach."},{"finding":"A lender using LightGBM Full could approve roughly fourteen additional loans per hundred underbanked applicants without raising expected loss.","kind":"performance","quote":"A lender that currently declines every applicant without a bureau file could adopt LightGBM Full, set a threshold that maintains the loss rate of its prime book, and approve roughly fourteen additional loans per hundred underbanked applicants."},{"finding":"Sensitivity analysis shows that lowering the cutoff by four AUC points still keeps expected loss below three percent, acceptable for most installment products.","kind":"statistical","quote":"Sensitivity analysis in the notebook shows that lowering the cut off by four AUC points still keeps expected loss below three percent, a level acceptable for most installment products."},{"finding":"In 42% of cases where the prediction flips from reject to accept, changing a single variable (online shopping frequency, subscription cost, or phone age) is sufficient.","kind":"other","quote":"In forty two percent of cases where the prediction flips from reject to accept, changing just one variable online shopping frequency, subscription cost, or phone age is sufficient."}],"reported_performance":null,"out_of_sample":{"method":"cross-validation","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":34,"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":true,"code_url":"https://github.com/atalaydenknalbant/underbanked_risk_estimation","note":null},"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":"2026-11-14T17:18:56Z"},"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/"}