A Federated F-score Based Ensemble Model for Automatic Rule Extraction
This work addresses data privacy challenges in rule extraction for financial institutions, though it appears incremental as it builds on existing federated learning and ensemble methods.
The paper tackles the problem of automatic rule extraction while preserving data privacy by proposing Fed-FEARE, a federated F-score based ensemble model, which significantly improves model performance measures compared to non-federated approaches and has been applied in real-world financial scenarios like anti-fraud and precision marketing.
In this manuscript, we propose a federated F-score based ensemble tree model for automatic rule extraction, namely Fed-FEARE. Under the premise of data privacy protection, Fed-FEARE enables multiple agencies to jointly extract set of rules both vertically and horizontally. Compared with that without federated learning, measures in evaluating model performance are highly improved. At present, Fed-FEARE has already been applied to multiple business, including anti-fraud and precision marketing, in a China nation-wide financial holdings group.