Collusion Detection Economics Causal Analysis
Our Research Focus
We investigate how GNNs and relational structures can be leveraged to solve complex reasoning tasks. Our work spans from Message Passing Neural Networks to Higher-Order Graph Networks, emphasizing robustness, interpretability, and scalability.
Core Research Streams
Available in: Python R Julia REST API
MODEL
Coming Soon
Collusion Detection →
Python R Julia
Applying GNNs to identify structural anomalies and fraudulent cyclic patterns in public tender datasets and financial networks.
MODEL
Coming Soon
Causal Analysis →
Python
Uncovering cause-and-effect relationships in graph data to distinguish true influence from spurious correlations.
DATABASE
Coming Soon
Public Procurement →
API Available for Researchers
100+ Databases
/
30 Countries
Large-scale graph dataset of government tenders, contracts, and supplier relationships for detecting bid-rigging collusion.
Access Restricted
These datasets are currently undergoing final verification.
Expected Release
Q3 2026