Taxonomic Recommendations of Real Estate Properties with Textual Attribute Information

TL;DR

This paper proposes an end-to-end method for creating a hierarchical taxonomy of real estate property attributes from textual data, enabling improved property recommendations based on search keywords.

Contribution

It introduces a novel methodology for constructing real estate taxonomies and demonstrates their application in hierarchical property recommendations.

Findings

Effective taxonomy construction metrics are proposed.

The approach improves recommendation relevance at different topical levels.

The methodology is validated through a real-world use case.

Abstract

In this extended abstract, we present an end to end approach for building a taxonomy of home attribute terms that enables hierarchical recommendations of real estate properties. We cover the methodology for building a real-estate taxonomy, metrics for measuring this structure's quality, and then conclude with a production use-case of making recommendations from search keywords at different levels of topical similarity.