CFRecs: Counterfactual Recommendations on Real Estate User Listing Interaction Graphs

TL;DR

CFRecs introduces a novel counterfactual graph learning framework combining GNNs and Graph-VAE to generate actionable, minimal modifications in real estate graphs, enhancing interpretability and recommendation effectiveness.

Contribution

This paper presents CFRecs, a new two-stage framework that leverages counterfactual reasoning in graph neural networks for actionable real estate recommendations.

Findings

Effective in generating minimal impactful graph modifications

Improves interpretability of recommendations in real estate data

Demonstrates success on Zillow's user-listing interaction data

Abstract

Graph-structured data is ubiquitous and powerful in representing complex relationships in many online platforms. While graph neural networks (GNNs) are widely used to learn from such data, counterfactual graph learning has emerged as a promising approach to improve model interpretability. Counterfactual explanation research focuses on identifying a counterfactual graph that is similar to the original but leads to different predictions. These explanations optimize two objectives simultaneously: the sparsity of changes in the counterfactual graph and the validity of its predictions. Building on these qualitative optimization goals, this paper introduces CFRecs, a novel framework that transforms counterfactual explanations into actionable insights. CFRecs employs a two-stage architecture consisting of a graph neural network (GNN) and a graph variational auto-encoder (Graph-VAE) to strategically propose minimal yet high-impact changes in graph structure and node attributes to drive desirable outcomes in recommender systems. We apply CFRecs to Zillow's graph-structured data to deliver actionable recommendations for both home buyers and sellers with the goal of helping them navigate the competitive housing market and achieve their homeownership goals. Experimental results on Zillow's user-listing interaction data demonstrate the effectiveness of CFRecs, which also provides a fresh perspective on recommendations using counterfactual reasoning in graphs.