Professor, Tabular Foundation Models and AutoML
Prior Labs
Prior Labs develops pre-trained tabular foundation models, such as TabPFN, for making predictions on structured data. These models deliver state-of-the-art results quickly without requiring model selection, tuning, or extensive preprocessing. The technology supports deployment across various environments, enabling faster machine learning pipelines in industries like finance, healthcare, and energy.
- Artificial Intelligence
- Data & Analytics
- Enterprise Software
- Software Only
Updated 20 months ago
Funding
Raised to date
$9.4MRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Funding rounds are not available yet.
Founders
Product
Problem
Traditional machine learning models struggle with tabular data, which is commonly found in spreadsheets and databases, due to its heterogeneous nature (text and numbers) and unclear relationships between data points. This makes it difficult to extract insights and make accurate predictions.
Solution
Prior Labs offers TabPFN, a tabular foundation model designed to understand and process structured data with unparalleled speed and accuracy. TabPFN delivers state-of-the-art results on classification, regression, and time-series tasks with minimal effort and no complex tuning required. The model can be fine-tuned on specific datasets to boost performance for unique use cases and industry challenges. It powers innovation across finance, healthcare, business analytics, and agriculture by turning structured data into actionable insights.
Target Audience
The primary audience includes data science teams in finance, healthcare, retail, logistics, and industrial sectors who require high-performance predictive models for structured data.
Features
- State-of-the-art predictive modeling for classification, regression, and imputation tasks
- Top-ranked time-series forecasting model, outperforming Amazon Chronos and Google TimesFM
- Fine-tuning capabilities to optimize performance on specific datasets
- Seamless integration with databases like Databricks, PostgreSQL, MySQL, MongoDB, Snowflake, BigQuery, Redshift, Oracle, and SQL Server
- Open-source TabPFN model with off-the-shelf performance for up to 10k samples and 500 features
- Web client for easy access to TabPFN without setup or tuning, running on Prior Labs GPU resources
- Premium enterprise option with early access to new features, fine-tuning on proprietary data, dedicated support, and enterprise-level GDPR compliance