xEM: Explainable Entity Matching in Customer 360

TL;DR

This paper introduces xEM, an explainable entity matching system for Customer 360 that aims to improve interpretability of matching decisions involving various entity types.

Contribution

The paper presents a novel explainable entity matching system, xEM, addressing the gap in interpretability for entity matching in Customer 360 applications.

Findings

xEM provides transparent explanations for matching decisions

The system supports multiple entity types including people, organizations, and locations

Demonstrates effectiveness in real-world Customer 360 scenarios

Abstract

Entity matching in Customer 360 is the task of determining if multiple records represent the same real world entity. Entities are typically people, organizations, locations, and events represented as attributed nodes in a graph, though they can also be represented as records in relational data. While probabilistic matching engines and artificial neural network models exist for this task, explaining entity matching has received less attention. In this demo, we present our Explainable Entity Matching (xEM) system and discuss the different AI/ML considerations that went into its implementation.