Kaggle is a data science competition platform and online community for data scientists and machine learning practitioners under Google LLC. It enables users to find and publish datasets, explore and build models in a web-based data science environment, collaborate with other data scientists and machine learning engineers, and enter competitions to solve data science challenges. The platform has become a central hub for artificial intelligence research and practical model development.
History
Kaggle was founded by Anthony Goldbloom in April 2010. Jeremy Howard, one of the first Kaggle users, joined in November 2010 and served as President and Chief Scientist. Nicholas Gruen served as the founding chair. In 2011, the company raised $12.5 million, and Max Levchin became chairman. On March 8, 2017, Fei-Fei Li, Chief Scientist at Google, announced that Google was acquiring Kaggle.
In June 2017, Kaggle surpassed 1 million registered users. As of October 2023, it had over 15 million users in 194 countries. In 2022, founders Goldbloom and Ben Hamner stepped down from their positions, and D. Sculley became CEO. In February 2023, Kaggle introduced Models, allowing users to discover and use pre-trained models with deep integrations into the rest of the platform. In April 2025, Kaggle partnered with the Wikimedia Foundation.
Competitions
Many machine-learning competitions have been run on Kaggle since its founding. Notable competitions include gesture recognition for Microsoft Kinect, creating an association football AI for Manchester City, coding a trading algorithm for Two Sigma Investments, and improving the search for the Higgs boson at CERN.
The competition host prepares the data and a description of the problem, and may choose whether to offer a monetary prize or run it unpaid. Participants experiment with different techniques and compete to produce the best models. Work is shared publicly through Kaggle Kernels to achieve better benchmarks and inspire new ideas. Submissions can be made via Kaggle Kernels, manual upload, or the Kaggle API. For most competitions, submissions are scored immediately based on predictive accuracy relative to a hidden solution file, and results are summarized on a live leaderboard. After the deadline, the host pays the prize money in exchange for a worldwide, perpetual, irrevocable, and royalty-free license to use the winning entry, which is non-exclusive unless otherwise specified.
Alongside public competitions, Kaggle offers private competitions limited to top participants. It also provides a free tool for data science teachers to run academic machine-learning competitions and hosts recruiting competitions where data scientists compete for interviews at companies like Facebook, Winton Capital, and Walmart.
Kaggle competitions have led to successful projects in HIV research, chess ratings, and traffic forecasting. Geoffrey Hinton and George Dahl used deep neural networks to win a competition hosted by Merck. Vlad Mnih, one of Hinton's students, used deep neural networks to win a competition hosted by Adzuna, and the technique was subsequently adopted by others in the community. Tianqi Chen from the University of Washington used Kaggle to demonstrate the power of XGBoost, which has since replaced Random Forest as a primary method for winning competitions. Several academic papers have been published based on findings from Kaggle competitions, aided by the live leaderboard that encourages continued innovation. Winning methods are frequently documented on the Kaggle Winner's Blog.
Progression System
Kaggle has implemented a progression system to recognize and reward users based on contributions and achievements. The system consists of five tiers: Novice, Contributor, Expert, Master, and Grandmaster. Each tier is achieved by meeting specific criteria in competitions, datasets, kernels (code-sharing), and discussions.
The highest tier, Kaggle Grandmaster, is awarded to users who have ranked at the top of multiple competitions, including high ranking in a solo team. As of April 2, 2025, out of 23.29 million Kaggle accounts, 2,973 had achieved Kaggle Master status and 612 had achieved Kaggle Grandmaster status.
Kaggle Notebooks
Kaggle includes a free, browser-based online integrated development environment called Kaggle Notebooks, designed for data science and machine learning. Users can write and execute code in Python or R, import datasets, use popular libraries, and train models on CPUs, GPUs, or TPUs directly in the cloud. This environment is often used for competition submissions, tutorials, education, and exploratory data analysis.
Medical Research Problems
In December 2025, an article in The Transmitter reported that Springer Nature retracted and removed nearly 40 publications that trained neural networks on a 'bonkers' dataset. The dataset, uploaded to Kaggle, contained photographs of autistic and non-autistic children's faces, with more than 2,900 images. It is unlikely that the children or their families gave consent for use in medical research, nor was ethical approval obtained. The articles using the dataset were retracted from the scientific literature, and at least 90 other publications cite a version of the dataset.
In April 2026, two additional datasets with no data provenance were identified on Kaggle and published in Nature under the title 'Dozens of AI disease-prediction models were trained on dubious data'. These datasets were used in 125 clinical prediction models, at least two of which have been used in hospitals in Indonesia and Spain, while one article using the dataset was referenced in a medical device patent. As of June 5, 2026, five of the articles using these datasets had been retracted.
In May 2026, an additional research publication using two image datasets from Kaggle came under investigation in Scientific Reports. An article in Retraction Watch, titled 'Comically bad datasets used to train clinical models for stroke and diabetes', highlighted that the images included famous actors such as Sylvester Stallone as Rambo, George Clooney, Angelina Jolie, and Daniel Craig, as well as children. Using child images in medical research without consent would be unethical. Reverse image searching revealed that some images were not for stroke but for Bell's palsy. One of the datasets is no longer available on Kaggle, while the other remains and mentions the image provenance issue.