A Federated F-score Based Ensemble Model for Automatic Rule Extraction

TL;DR

This paper introduces Fed-FEARE, a federated ensemble tree model that enables multiple agencies to collaboratively extract rules while preserving data privacy, significantly improving performance over non-federated methods.

Contribution

It presents a novel federated ensemble model for automatic rule extraction that works across multiple agencies without sharing raw data.

Findings

Enhanced model performance with federated learning

Successful application in anti-fraud and marketing

Preserves data privacy during rule extraction

Abstract

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.