New AI model can generate real-world tabular data
A new AI model has been launched that can generate highly realistic tabular data – the type of structured data widely used in healthcare, finance, and social science.
The new method, called TabCascade, addresses a long-standing challenge in artificial intelligence: while generative AI has made remarkable progress in creating realistic images, videos, text, proteins, and other forms of data, generating realistic tabular data has remained significantly more difficult.
The model was developed by PhD candidate Markus Mueller, Kathrin Gruber, and research fellow Dennis Fok from the Econometric Institute at Erasmus School of Economics. They will present their findings at the Forty-Third International Conference on Machine Learning, one of the global top three conferences on AIOpens external. This year, it will be held in Seoul, South Korea from 6-11 July. Additionally, the code of the model has been made publicly available.
Read more about this project on the website of the Erasmus School of Economics.