{"paper_id":"2502.15726","title":"Bankruptcy analysis using images and convolutional neural networks (CNN)","authors":["Luiz Tavares","Jose Mazzon","Francisco Paletta","Fabio Barros"],"paper_date":"2025-01-29","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2502.15726v1","page_url":"https://thequant.space/flowcharts/bankruptcy-analysis-using-images-and-convolutional-neural-ne/","scores":{"empirical_rigor":6,"math_complexity":4.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes generating image representations of SME financial data for analysis with a GoogLeNet-based convolutional neural network to predict default risk.","quote":"this study introduces a method for evaluating SMEs by generating images for processing via a convolutional neural network (CNN).","summary":"The marketing departments of financial institutions strive to craft products and services that cater to the diverse needs of businesses of all sizes. However, it is evident upon analysis that larger corporations often receive a more substantial portion of available funds. This disparity arises from…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"A sufficiently large number of images is required for the CNN to achieve high predictive performance.","type":"data","stated":"explicit","quote":"The quantity of images, therefore, emerges as a critical factor influencing the enhancement of CNN outcomes."},{"assumption":"Images constructed from accounting account data capture relevant information for default prediction.","type":"model","stated":"implied","quote":"For Division 47, as elucidated in Section 4.2, the models constructed from images based on accounting account data yielded exceptionally reliable predictions"}]},"datasets":{"status":"available","items":[{"name":"SME enterprise dataset","provider":null,"kind":"fundamentals","access":"unknown","period":null,"universe":"105,000 enterprises across divisions 47, 86, 82","quote":"Within the broader dataset of 105,000 enterprises, a subset of 14,456 companies was extracted based on these categories."},{"name":"Monthly data vectors for Division 47","provider":null,"kind":"fundamentals","access":"unknown","period":null,"universe":"Division 47 firms","quote":"a total of 416,710 monthly data vectors were compiled for Division 47"},{"name":"Monthly data vectors for Division 86","provider":null,"kind":"fundamentals","access":"unknown","period":null,"universe":"Division 86 firms","quote":"an additional 116,487 vectors for Division 86"}],"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 CNN achieved 97.8% accuracy when trained on a large set of SME images.","kind":"predictive-accuracy","quote":"The findings demonstrate a significant predictive capacity, achieving 97.8% accuracy, when a substantial number of images are utilized."},{"finding":"Models using accounting‑based images for Division 47 reached accuracy exceeding 95% and high test accuracy.","kind":"predictive-accuracy","quote":"... the models constructed from images based on accounting account data yielded exceptionally reliable predictions, as evidenced by their high accuracy and test accuracy rates."},{"finding":"Combining Division 86 with Division 47 data raised accounting‑image model accuracy to 96.4% and F1 Score to 97.9%.","kind":"predictive-accuracy","quote":"In the case of the model based on accounting account imagery, accuracy escalated to 96.4%, with F1 Score achieving 97.9% — the highest in all training iterations"},{"finding":"When tested on Division 86 alone, the combined model improved test F1 Score to 93.6% versus 71.5% for the single‑division model.","kind":"predictive-accuracy","quote":"establishing the combined model as superior to the one trained exclusively on Division 86 data."},{"finding":"Divisions with fewer than 4,610 images showed lower accuracy (minimum 92.2%) and higher loss rates.","kind":"performance","quote":"beyond 4,610, the lowest recorded accuracy was 92.2%, although this did not uniformly translate to a low rate of model loss—as evidenced by a 24.2% loss rate in the third training iteration."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":27,"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":"2026-11-14T17:46:22Z"},"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/"}