Computational and statistical research in data science and machine learning, basic and applied, to harness large databases on health and society.
Overview
We are an Inria team doing research at the intersection between machine-learning, databases, and quantitative social sciences (eg empirical economy, epidemiology…).
The Soda team is a spin-off from the Parietal team, located in Inria Saclay.
We are looking for interns, postdocs!
Research axes
- Representation learning for heterogeneous databases
- Learning despite database normalization errors
- Tabular deep learning
- Data-science with statistical learning
- Statistical learning with missing values
- Machine learning for causal inference
- Health and Social Sciences
- Electronic health records
- Epidemiological cohorts
- Educational data mining
- Turn-key machine-learning tools for socio-economic impact
Helping to maintain and grow tools such as scikit-learn, joblib…
