Research

Research Summary

At CEADS, we transform data science into the art of drawing reliable causal evidences. We partner with domain experts across a vast spectrum of critical challenges—from estimating disease prevalence and understanding deforestation in Madagascar, to quantifying the socio-economic burden of health shocks. We commit to delivering solutions that are Accurate, Trustworthy and Domain-Conscious

Data Fusion for Causal Inference

Double Machine Learning for Combining Experimental and Observational Studies
Data Fusion for Partial Identification of Causal Effects
Integrating Data with Disparate Outcome Measures
Who Are We Missing? A Principled Approach to Characterizing the Underrepresented Population
Regularizing Extrapolation under Positivity Violation
Toward Generalizing Trials Inferences to Target Population

Interpretable ML for Causal Inference

Matching After Learning to Stretch
Variable Importance Matching
Rashomon Set of Optimal Trees
Causal Inference for Distributional Data
Regularizing Extrapolation in Causal Inference

AI Sandbox for Causal Inference

Validating Causal Inference Methods
Controllable Generative Sandbox for Causal Inference
How many patients do you need?

Causal Inference for Networks

Causal Relational Learning
Graph Machine Learning based DML Estimator for Network Causal Effects
Transporting Effects Across Networks

Experienced Burden of Diseases

Breast cancer and income loss in Denmark: heterogeneous outcomes and longitudinal effects
The Lasting Income Costs of Illness

Anthropogenic Threats to Biodiversity

Income & Deforestation: Evidence from a Natural Experiment in Madagascar
Vanilla farming shapes wildlife hunting pressures in northeast Madagascar

Google Sites

Report abuse