{"paper_id":"2508.02738","title":"CreditARF: A Framework for Corporate Credit Rating with Annual Report and Financial Feature Integration","authors":["Yumeng Shi","Zhongliang Yang","DiYang Lu","Yisi Wang","Yiting Zhou","Linna Zhou"],"paper_date":"2025-08-02","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2508.02738v1","page_url":"https://thequant.space/flowcharts/creditarf-a-framework-for-corporate-credit-rating-with-annu/","scores":{"empirical_rigor":8.5,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a novel framework that integrates financial data with features extracted from corporate annual reports using large language models.","quote":"In response, we propose a novel framework that integrates financial data with features from corporate annual reports.","summary":"Corporate credit rating serves as a crucial intermediary service in the market economy, playing a key role in maintaining economic order. Existing credit rating models rely on financial metrics and deep learning. However, they often overlook insights from non-financial data, such as corporate…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Annual reports are divided into N batches for processing by the Transformer encoder.","type":"model","stated":"explicit","quote":"For an annual report, it is assumed to be divided into N batches."},{"assumption":"Corporate credit rating is treated as a multi‑class classification problem over seven rating categories.","type":"model","stated":"explicit","quote":"Corporate credit rating is formulated as a multi-class classification task."},{"assumption":"The original 23 rating grades are consolidated into 7 major categories for the experiments.","type":"data","stated":"explicit","quote":"the 23 rating grades were consolidated into 7 major categories: AAA, AA, A, BBB, BB, B, and CCC."},{"assumption":"Financial numerical features are extracted using existing CNN, GNN, or RNN models and then combined with annual report features.","type":"model","stated":"explicit","quote":"we try to supplement the aforementioned financial numerical feature extraction models MFNF with the features of the annual report extracted by large models"},{"assumption":"The dataset contains 2,307 samples with 20 financial attributes and annual report documents.","type":"data","stated":"explicit","quote":"This process resulted in a new dataset containing 2,307 samples, which integrates 20 financial attributes and annual report documents."}]},"datasets":{"status":"available","items":[{"name":"Comprehensive Corporate Rating Dataset (CCRD)","provider":"constructed by authors using Kaggle financial data and annua","kind":"fundamentals","access":"public","period":"2010-2016","universe":"U.S. publicly listed companies","quote":"we have developed the Comprehensive Corporate Rating Dataset (CCRD), a large-scale dataset that combines traditional financial data with annual report data.","known_id":"kaggle"}],"known":[{"id":"kaggle","name":"Kaggle","provider":"Kaggle","kind":"other","access":"public","quote":"We obtained a dataset containing only financial data from Kaggle TABLE I ANNUAL REPORT INFORMATION FOR A SUBSET OF U.S. PUBLICLY LISTED COMPANIES Company Name Years Avnet Inc. 2010-2016 Automatic Data Processing Inc. 2010-2016 Carpenter Technology Corp. 2010-2016 General Mills Inc. 2010-2016 Micron Technology Inc. 2010-2016 Compass Group PLC 2010-2016 Belden Inc. 2011-2016 AstraZeneca PLC 2011-2016 Target Corp. 2011-","mentions":1,"used_in":1}],"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":"Adding annual report features (ARF) improves overall rating accuracy by approximately 8% to 12% across all models.","kind":"predictive-accuracy","quote":"After adding annual report features (ARF), the accuracy improved by approximately 8% to 12% across all models."},{"finding":"The BB rating category shows the largest precision improvement, exceeding 20% when ARF are incorporated.","kind":"performance","quote":"Among the seven rating categories, the BB category showed the largest precision improvement, exceeding 20%."},{"finding":"GNN‑based baseline models benefit the most from ARF integration, with performance gains close to 12%.","kind":"performance","quote":"Among the three baseline models, the GNN-based models benefited the most from the integration of ARF features, with an improvement close to 12%."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":17,"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":"2026-11-14T17:30:44Z"},"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/"}