{ "fetched_at": "2026-10-19T15:03:22Z", "source_url": "https://www.kaggle.com/competitions/company-bankruptcy-prediction/data", "pages": [ { "name": "data-description", "content": "The purpose of the bankruptcy prediction is to assess the financial condition of a company and its future perspectives within the context of longterm operation on the market\n\n## Data Set Information:\n\nThe dataset is about bankruptcy prediction of Polish companies. The data was collected from Emerging Markets Information Service, which is a database containing information on emerging markets around the world. The bankrupt companies were analyzed in the period 2000-2012, while the still operating companies were evaluated from 2007 to 2013.\n\n## KPIs:\n\nThe performance of the competitors will be evaluated based on the F1 score. Higher F1 score will be ranked higher in the final ranking\n\n## Files\n\n* **train.csv** - the training set that includes labels (1 means bankruptcy, 0 means not bankruptcy)\n* **test.csv** - the test set that do not include labels\n* **sample_submission.csv** - a sample submission file in the correct format\n* **metaData.csv** - supplemental information about the data\n\n## Columns\n* `net profit / total assets`\n* `total liabilities / total assets`\n* `working capital / total assets`\n* `current assets / short-term liabilities`\n* `[(cash + short-term securities + receivables - short-term liabilities) / (operating expenses - depreciation)] * 365`\n* `retained earnings / total assets`\n* `EBIT / total assets`\n* `book value of equity / total liabilities`\n* `sales / total assets`\n* `equity / total assets`\n* `(gross profit + extraordinary items + financial expenses) / total assets`\n* `gross profit / short-term liabilities`\n* `(gross profit + depreciation) / sales`\n* `(gross profit + interest) / total assets`\n* `(total liabilities * 365) / (gross profit + depreciation)`\n* `(gross profit + depreciation) / total liabilities`\n* `total assets / total liabilities`\n* `gross profit / total assets`\n* `gross profit / sales`\n* `(inventory * 365) / sales`\n* `sales (n) / sales (n-1)`\n* `profit on operating activities / total assets`\n* `net profit / sales`\n* `gross profit (in 3 years) / total assets`\n* `(equity - share capital) / total assets`\n* `(net profit + depreciation) / total liabilities`\n* `profit on operating activities / financial expenses`\n* `working capital / fixed assets`\n* `logarithm of total assets`\n* `(total liabilities - cash) / sales`\n* `(gross profit + interest) / sales`\n* `(current liabilities * 365) / cost of products sold`\n* `operating expenses / short-term liabilities`\n* `operating expenses / total liabilities`\n* `profit on sales / total assets`\n* `total sales / total assets`\n* `(current assets - inventories) / long-term liabilities`\n* `constant capital / total assets`\n* `profit on sales / sales`\n* `(current assets - inventory - receivables) / short-term liabilities`\n* `total liabilities / ((profit on operating activities + depreciation) * (12/365))`\n* `profit on operating activities / sales`\n* `rotation receivables + inventory turnover in days`\n* `(receivables * 365) / sales`\n* `net profit / inventory`\n* `(current assets - inventory) / short-term liabilities`\n* `(inventory * 365) / cost of products sold`\n* `EBITDA (profit on operating activities - depreciation) / total assets`\n* `EBITDA (profit on operating activities - depreciation) / sales`\n* `current assets / total liabilities`\n* `short-term liabilities / total assets`\n* `(short-term liabilities * 365) / cost of products sold)`\n* `equity / fixed assets`\n* `constant capital / fixed assets`\n* `working capital`\n* `(sales - cost of products sold) / sales`\n* `(current assets - inventory - short-term liabilities) / (sales - gross profit - depreciation)`\n* `total costs /total sales`\n* `long-term liabilities / equity`\n* `sales / inventory`\n* `sales / receivables`\n* `(short-term liabilities *365) / sales`\n* `sales / short-term liabilities`\n* `sales / fixed assets`", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "We are pleased to cordially invite university students, who consider Data Science and related fields their careers, to attend the 3rd International Competition in Data Science & Artificial Intelligence, organized by The International Society of Data Scientists. Students graduated within 5 years are eligible to attend. Each team can optionally have an advisor, who may be a professor or a data science professional. The competition is to create a playground for young Data Scientists to grow skills, knowledge, experience, and collaboration for their career path. The competition committee includes professors and industry leaders around the world.\n\nWill you be able to predict if a company would be going bankrupt in the future? Given the bankruptcy dataset, your task is to tell which ones would be going bankrupt. Your team will submit the result for evaluation at the end of the competition.\n\nThe committee chairs of this competition track include:\nDr. Sebastian Tomczak, Department of Operations Research and Business Intelligence, Faculty of Management, Wroclaw University of Science and Technology, Wrocław, Poland\nDr. Gia Nhu Nguyen, Associate Professor & Dean of School of Computer Science, Duy Tan University, Vietnam\nDr. Christopher Do, ISODS President\nDr. Nam Nguyen, ISODS Vice President\nMr. Cory Wang, ISODS Vice President\n\n## About - The International Society of Data Scientists\n\nThe International Society of Data Scientists (or The ISODS), at www.isods.org, registered as a Massachusetts non-profit, is a professional organization for Data Science and AI practitioners and researchers, which may include Data Scientists, Machine Learning Scientists, AI Scientists, Data Analysts, Data Engineers, Software Engineers, Risk Analysts, Actuaries, Business Analysts, and more, who apply Data Science and AI at work. ISODS promotes Data Science and AI domestically in the United States as well as internationally via professional exams, competitions, conferences, training, and publications.\n\n## Acknowledgements\n\nWe thank Professor Sebastian Tomczak - Department of Operations Research, Wrocław University of Science and Technology, Poland for providing this dataset.\n\nWe thank [Professors and Industry Leaders](https://www.isods.org/news-times/item/27-competition-committee-for-the-3rd-annual-international-data-science-ai-competition-for-the-year-2022) who volunteer to participate and contribute in the competition committee.\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "The evaluation metric for this competition is [F1 score](https://en.wikipedia.org/wiki/F-score). Higher F1 score will be ranked higher in the final ranking. The F1 score, commonly used in information retrieval, measures accuracy using the statistics [precision and recall](https://en.wikipedia.org/wiki/Precision_and_recall).\n\nPrecision is the ratio of true positives to all predicted positives. Recall is the ratio of true positives to all actual positives. The F1 score is given by `2 * (precision * recall)/(precision + recall)`.\n\nThe F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.\n\n## Submission Format\n\nSubmission files (*.csv) should contain two columns: `id` and `class`. `class` is the labels of the test dataset predicted by the model.\n\nThe file should contain a header and have the following format:\n```\nid, class\n1,1\n2,0\n3,1\n```", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "Rules include the following\n - Don't cheat!\n - Apply yourself!\n - Have fun!\n\nAfter the competition deadline, participating teams should be able to make their notebooks public. In the notebook, students can provide more information about their team, such as university names and locations, advisor (if applicable), etc.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "What To Earn", "content": "The competition is to provide experience to young data scientists, who are students. We do not offer cash prizes according to Kaggle's rules. Instead, top performers will be selected to submit their reports as conference papers in the related conference by ISODS, and considered passing the ISODS Machine Learning (ML) exam if using the relevant approaches.\n\n`The ISODS provides professional exams toward several designations of the Society, including Associate Master (CM), Fellow Master (FM), and Grandmaster (GM). These titles are not related to similar titles by Kaggle.`", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Timeline", "content": "Start Date - March 28, 2022\n\nEntry Deadline - Same as the Final Submission Deadline.\n\nTeam Merger Deadline - Same as the Final Submission Deadline.\n\nFinal Submission Deadline - June 19, 2022\n\nAll deadlines are at 11:59 PM UTC on the corresponding day unless otherwise noted. The competition organizers reserve the right to update the contest timeline if they deem it necessary.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "All The Tracks", "content": "All Kaggle-based Community Competition Tracks are:\n\n1> Company Bankruptcy Prediction\nhttps://www.kaggle.com/c/company-bankruptcy-prediction\n\n2> Classification of plants of Southeast Asia\nhttps://www.kaggle.com/c/classification-of-plants-of-southeast-asia\n\n3> Fashion and Beauty Review Classification\nhttps://www.kaggle.com/competitions/fashion-and-beauty-review-classification/\n\nThere is no limitation in term of the number of tracks a team or individual can participate.\n\nTop performers will be selected to submit their reports as conference papers in the related conference by ISODS. \n\nTop performers in track 1 are considered passing the ISODS Machine Learning exam; in track 2 as passing the Deep Learning 1 (DL1) exam; in track 3 as passing the Deep Learning 2 (DL2) exam. See more about ISODS Professional Exams organized by the International Institute of Data Science and Artificial Intelligence at ISODS website (https://www.isods.org).", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Committee", "content": "The [competition committee composition](https://www.isods.org/item/27-competition-committee-for-the-3rd-annual-international-data-science-ai-competition-for-the-year-2022) is as follows:\n\nDr. Krishna R. Pattipati, Board of Trustees Distinguished Professor & UTC Professor in Systems Engineering, Department of Electrical and Computer Engineering, University of Connecticut, Connecticut, USA\n\nDr. Rajakumar Arul, Assistant Professor, School of Computer Science and Engineering (SCOPE), Vellore Institute of Technology (VIT) Chennai Campus, India\n\nMarc Böhlen, Professor, Department of ART, Emerging Practices in Computational Media, University at Buffalo, New York, USA\n\nDr. Mohammad Soltanieh-ha, Assistant Professor, Questrom School of Business, Boston University, Massachusetts, USA\n\nDr. Manar Alalfi, Associate Professor in Software Engineering, Ryerson University, Toronto, Ontario M5B 2K3, Canada; Adjunct Assistant Professor, Queen's University School of Computing, Kingston, Ontario K7L 3N6, Canada\n\nDr. Sebastian Tomczak, Department of Operations Research and Business Intelligence, Faculty of Management, Wroclaw University of Science and Technology, Wrocław, Poland\n\nDr. Shaimaa Ali, Assistant Professor (Software Engineering) at the Electrical and Computer Engineering Department, Western University, London, Ontario N6A 3K7, Canada\n\nDr. Renzhi Cao, Assistant Professor, Department of Computer Science, Pacific Lutheran University, Washington, USA\n\nDr. Adisak Sukul, Associate Teaching Professor at Department of Computer Science, Iowa State University, Iowa, USA\n\nDr. Haiyang Kong, Assistant Professor, Business School of Beijing Normal University, Beijing, China\n\nDr. Nguyet Nguyen, Associate Professor, Youngstown State University, Ohio, USA\n\nDr. Hoa Trung Dinh, Assistant Professor, Troy University, Alabama, USA\n\nDr. Kim Phuc Tran, Associate Professor, University of Lille, Lille, France\n\nDr. Lan Vu, Professor, Department Head and Chair at Hanoi University of Public Health, Vietnam\n\nDr. Duy Nguyen, Assistant Professor, Marist College, New York, USA\n\nDr. Hoan Nguyen, Computer Scientist, Jackson Lab, Connecticut, USA\n\nDr. Bay Dinh Vo, Associate Professor, HUTECH University of Technology, Vietnam\n\nDr. Son P Nguyen, Lecturer at University of Economics and Law, Vietnam\n\nDr. Vinh Dang, Lecturer, Information Technology Faculty, Industrial University of HCM City, Vietnam\n\nDr. Gia Nhu Nguyen, Associate Professor & Dean of School of Computer Science, Duy Tan University, Vietnam\n\nDr. Bao The Pham, Associate Professor at Saigon University, Vietnam\n\nDr. Loan Nguyen, Associate Professor at International University, Vietnam\n\nDr. Christopher Do, ISODS President, Massachusetts, USA\n\nDr. Nam Nguyen, ISODS Vice President and Staff Data Scientist at Wayfair, Texas, USA\n\nMr. Cory Wang, ISODS Vice President, Connecticut, USA\n\nDr. Phu Vu, Regional Research Director, WorldQuant, Vietnam\n\nDr. Quang Hieu Vu, Head of Data Platform, ZaloPay\n\nDr. Nam Thanh Nguyen, FUNiX Founder, Former FPT CEO\n\nDr. Jianmo Ni, Software Engineer, Google\n\nISODS thanks to all the voluntary work by committee members, and looks forward to the participation and contribution. We would like to thank all the authors who contributed their datasets to the competition tracks as well. ", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Other Credits", "content": "We would like to thank Addison Howard and Laurie White at Google, who help during the setting-up phase.", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Paper Template", "content": "If your team is invited to submit a conference paper, [download the paper template PDSAI_Template.docx here](https://github.com/isods/templates)", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }