{"paper_id":"2503.18029","title":"Unleashing the power of text for credit default prediction: Comparing human-written and generative AI-refined texts","authors":["Zongxiao Wu","Yizhe Dong","Yaoyiran Li","Baofeng Shi"],"paper_date":"2025-03-23","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2503.18029v1","page_url":"https://thequant.space/flowcharts/unleashing-the-power-of-text-for-credit-default-prediction/","scores":{"empirical_rigor":7.5,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes using ChatGPT‑refined loan assessment texts together with structured data to improve credit default prediction models.","quote":"Using deep learning techniques, we show that incorporating unstructured text data, particularly ChatGPT-refined texts, alongside conventional structured data significantly enhances credit default predictions.","summary":"This study explores the integration of a representative large language model, ChatGPT, into lending decision-making with a focus on credit default prediction. Specifically, we use ChatGPT to analyse and interpret loan assessments written by loan officers and generate refined versions of these…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Missing continuous features are imputed with their mean values.","type":"data","stated":"implied","quote":"In cases where continuous features are missing, they are filled with the means of the features"},{"assumption":"Default is defined as 90 days past payment due.","type":"other","stated":"explicit","quote":"Default is defined as 90 days past payment due."}]},"datasets":{"status":"available","items":[{"name":"mSE loan dataset","provider":"Chinese bank (national basis)","kind":"alternative","access":"proprietary","period":"December 2008 to July 2009","universe":"micro and small business loans (2,460 loans)","quote":"final sample consists of 2,460 loans with durations ranging from 1 to 8 months, originating between December 2008 and July 2009."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"unclear"},"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":"ChatGPT‑refined texts improve predictive accuracy compared to human‑written texts when added to structured data.","kind":"predictive-accuracy","quote":"While both texts benefit credit scoring models (compared to models using only structured data), ChatGPT-refined texts can lead to more accurate prediction results in most cases."},{"finding":"Models using both negative and positive factors from ChatGPT‑refined texts generally outperform those using other text choices.","kind":"performance","quote":"models which utilise the negative+positive text generally outperform those using other text choices."},{"finding":"AI‑refined text is less effective for PRAUC than human‑written text.","kind":"negative","quote":"the PRAUC results indicate that AI-refined text is less effective at predicting credit defaults compared to human-written texts."},{"finding":"In most cases, models based on ChatGPT‑refined texts yield higher profitability than those based on human‑written texts.","kind":"performance","quote":"find that, in most cases, the latter yields higher profitability than the former."},{"finding":"ChatGPT's analysis of borrower delinquency contributes the most to improving predictive accuracy.","kind":"predictive-accuracy","quote":"Moreover, we find that ChatGPT's analysis of borrower delinquency contributes the most to improving predictive accuracy."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":36,"citations":{"cited_by_in_corpus":1,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"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":"2026-11-14T17:42:02Z"},"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/"}