{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T22:30:36Z","timestamp":1780612236836,"version":"3.54.1"},"reference-count":23,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T00:00:00Z","timestamp":1751846400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Predicting company bankruptcy is a critical task in financial risk assessment. This study introduces a novel approach using Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs) to enhance bankruptcy prediction accuracy. By transforming financial statements into grayscale images and leveraging synthetic data generation, we analyze a dataset of 6249 companies, including 3256 active and 2993 bankrupt firms. Our methodology innovates by addressing dataset limitations through GAN-based data augmentation. CNNs are employed to take advantage of their ability to extract hierarchical patterns from financial statement images, providing a new approach to financial analysis, while GANs help mitigate dataset imbalance by generating realistic synthetic data for training. We generate synthetic financial data that closely mimics real-world patterns, expanding the training dataset and potentially improving classifier performance. The CNN model is trained on a combination of real and synthetic data, with strict separation between training\/validation and testing.<\/jats:p>","DOI":"10.3390\/make7030063","type":"journal-article","created":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T06:03:13Z","timestamp":1751868193000},"page":"63","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A Novel Approach to Company Bankruptcy Prediction Using Convolutional Neural Networks and Generative Adversarial Networks"],"prefix":"10.3390","volume":"7","author":[{"given":"Alessia","family":"D\u2019Ercole","sequence":"first","affiliation":[{"name":"Department of Law, Economics, Politics, and Modern Languages, LUMSA University, 00192 Rome, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gianluigi","family":"Me","sequence":"additional","affiliation":[{"name":"Department of Economics and Finance, Luiss Guido Carli University, 00198 Rome, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"743","DOI":"10.1016\/j.ejor.2018.10.024","article-title":"Deep learning models for bankruptcy prediction using textual disclosures","volume":"274","author":"Mai","year":"2019","journal-title":"Eur. J. Oper. Res."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.eswa.2016.04.001","article-title":"Ensemble Boosted Trees with Synthetic Features Generation in Application to Bankruptcy Prediction","volume":"58","author":"Tomczak","year":"2016","journal-title":"Expert Syst. Appl."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Alaminos, D., Garc\u00eda, A.D., and Fern\u00e1ndez-G\u00e1mez, M. (2018). Correction: A Global Model for Bankruptcy Prediction. PLoS ONE, 13.","DOI":"10.1371\/journal.pone.0208476"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1016\/j.eswa.2017.10.040","article-title":"A systematic review and critical evaluation of bankruptcy prediction models: Towards a framework for tool selection","volume":"94","author":"Alaka","year":"2018","journal-title":"Expert Syst. Appl."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1016\/j.eswa.2018.09.039","article-title":"Bankruptcy prediction using imaged financial ratios and convolutional neural networks","volume":"117","author":"Hosaka","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"352","DOI":"10.2478\/ceej-2021-0024","article-title":"Modelling cross-sectional tabular data using convolutional neural networks: Prediction of corporate bankruptcy in Poland","volume":"8","author":"Odziemczyk","year":"2021","journal-title":"Cent. Eur. Econ. J."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"10859","DOI":"10.1007\/s10462-024-10859-3","article-title":"Breaking the data barrier: A review of deep learning techniques for democratizing AI with small datasets","volume":"57","author":"Rather","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"101844","DOI":"10.1016\/j.ribaf.2022.101844","article-title":"Bankruptcy prediction using fuzzy convolutional neural networks","volume":"64","author":"Serret","year":"2023","journal-title":"Res. Int. Bus. Financ."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative Adversarial Networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Nayak, S.M., and Rout, M. (2024). Bankruptcy prediction using a GAN-based data augmentation hybrid model. Generative AI: Current Trends and Applications, Springer.","DOI":"10.1007\/978-981-97-8460-8_19"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"6249","DOI":"10.1007\/s11042-023-15747-6","article-title":"Generative adversarial network based synthetic data training model for lightweight convolutional neural networks","volume":"83","author":"Rather","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Nalayini, C.M., Katiravan, J., Sathyabama, A.R., Rajasuganya, P.V., and Abirami, K. (2023). Identification and detection of credit card frauds using CNN. Applications of Computational Intelligence in Management & Mathematics, Springer.","DOI":"10.1007\/978-3-031-25194-8_22"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Akhtar, M.S., and Feng, T. (2022). Detection of malware by deep learning as CNN-LSTM machine learning techniques in real time. Symmetry, 14.","DOI":"10.3390\/sym14112308"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"120714","DOI":"10.1016\/j.eswa.2023.120714","article-title":"Bankruptcy prediction using machine learning models with the text-based communicative value of annual reports","volume":"233","author":"Chen","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_15","first-page":"1291","article-title":"Designing topological data to forecast bankruptcy using convolutional neural networks","volume":"325","year":"2022","journal-title":"Ann. Oper. Res."},{"key":"ref_16","first-page":"41","article-title":"Predicting bankruptcy at Polish companies: A comparison of selected machine learning and deep learning algorithms","volume":"6","author":"Wyrobek","year":"2019","journal-title":"Krakow Rev. Econ. Manag.\/Zesz. Nauk. Uniw. Ekon. Krk."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"885","DOI":"10.1007\/s10479-022-04766-5","article-title":"Deep learning-based model for financial distress prediction","volume":"345","author":"Elhoseny","year":"2022","journal-title":"Ann. Oper. Res."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.future.2018.07.045","article-title":"DRTHIS: Deep ransomware threat hunting and intelligence system at the fog layer","volume":"90","author":"Homayoun","year":"2019","journal-title":"Future Gener. Comput. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Almomani, I., Alkhayer, A., and El-Shafai, W. (2023). E2E-RDS: Efficient End-to-End Ransomware Detection System Based on Static-Based ML and Vision-Based DL Approaches. Sensors, 23.","DOI":"10.3390\/s23094467"},{"key":"ref_20","first-page":"1","article-title":"Ransomware Detection with CNN and Deep Learning Based on Multiple Features of Portable Executable Files","volume":"81","author":"Yang","year":"2023","journal-title":"Res. Square"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Singh, A., Handa, A., Kumar, N., and Shukla, S.K. (2019). Malware Classification Using Image Representation. Cyber Security Cryptography and Machine Learning, CSCML 2019, Beer Sheva, Israel, 27\u201328 June 2019, Springer.","DOI":"10.1007\/978-3-030-20951-3_6"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Omar, M. (2022). New Approach to Malware Detection Using Optimized Convolutional Neural Network. Machine Learning for Cybersecurity, Springer International Publishing.","DOI":"10.1007\/978-3-031-15893-3_2"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Ben Atitallah, S., Driss, M., and Almomani, I. (2022). A Novel Detection and Multi-Classification Approach for IoT-Malware Using Random Forest Voting of Fine-Tuning Convolutional Neural Networks. Sensors, 22.","DOI":"10.3390\/s22114302"}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/3\/63\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:05:37Z","timestamp":1760033137000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/3\/63"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,7]]},"references-count":23,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["make7030063"],"URL":"https:\/\/doi.org\/10.3390\/make7030063","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,7]]}}}