Causal AI for Better Decisions
- The Challenge & Solution
The Challenge
- Correlation does not establish causation
- Predictive models can produce misleading recommendations
- Causal analysis currently requires specialist knowledge, technical software and extensive manual work
The ETIA Solution
- Automated causal discovery
- Causal reasoning
- Natural-language AI agent
- Visual explanations
- Decision support
- How ETIA Works
Data → Causal models
→ Insights & Decisions
3 Principal Components
- What ETIA can help answer
What could ETIA help us answer?
- What is causing a particular outcome?
- What would happen under a different decision?
- Which action is most likely to improve the desired result?
- What is the root cause of a failure?
- What might have happened if a different choice had been made?
- Application Areas
- Telecommunications
- Mobility and automotive safety
- Healthcare and bioinformatics
- Marketing and customer behaviour
- Industrial systems and infrastructure
- Scientific research
- Project Objectives
1
Causal Discovery Engine
2
Causal AI Agent
3
Technical Robustness
4
High-potential Value
5
Go-To Market Strategy
Develop a viable business model, go-to-market strategy, product roadmap, use-of-funds plan and IP protection strategy to prepare for investment and commercial scalability.
6
Build a Community
- Join the community
Join the Community
The ETIA project is building an open community of researchers, developers, industry experts and curious minds working to make causal discovery more accessible, robust and useful in the real world. Whether you want to contribute ideas, test the technology, explore new applications or simply follow the journey, there is a place for you here.
Join us in moving from correlation to understanding.
- News - Articles - Research
Nikos Gkorgkolis Presents Research on Large Causal Models at ECML PKDD 2026
ETIA researcher Nikolaos Gkorgkolis presented research on Large Causal Models for Temporal Causal Discovery at ECML PKDD 2026 in Naples, exploring how pretrained neural models can make causal discovery on time-series data faster, more scalable and more transferable across datasets.
Konstantina Biza Receives Honorable Mention for Student Best Paper Award at PGM 2026
ETIA researcher Konstantina Biza received an Honorable Mention for the Student Best Paper Award at PGM 2026 in Valencia for the paper “An AutoML-Powered Architecture for Causal Discovery,” co-authored with Sofia Triantafillou and Ioannis Tsamardinos.
ETIA Kicks Off: Two Days to Align Vision, Technology and the Road Ahead
ETIA officially launched with a two-day kick-off meeting at the University of Crete, bringing the team together to align on the project vision, technology roadmap, business development, communication priorities and the first concrete tasks for the months ahead.