Unveiling Location-Specific Price Drivers: A Two-Stage Cluster Analysis for Interpretable House Price Predictions

TL;DR

This paper introduces a two-stage clustering approach for house price prediction that improves interpretability and accuracy by modeling localized market variations in German real estate data.

Contribution

It presents a novel two-stage clustering method combined with interpretable models like LR and GAM for better localized house price valuation.

Findings

36% improvement in GAM mean absolute error

58% improvement in LR mean absolute error

Graphical analysis reveals pattern shifts between clusters

Abstract

House price valuation remains challenging due to localized market variations. Existing approaches often rely on black-box machine learning models, which lack interpretability, or simplistic methods like linear regression (LR), which fail to capture market heterogeneity. To address this, we propose a machine learning approach that applies two-stage clustering, first grouping properties based on minimal location-based features before incorporating additional features. Each cluster is then modeled using either LR or a generalized additive model (GAM), balancing predictive performance with interpretability. Constructing and evaluating our models on 43,309 German house property listings from 2023, we achieve a 36% improvement for the GAM and 58% for LR in mean absolute error compared to models without clustering. Additionally, graphical analyses unveil pattern shifts between clusters. These findings emphasize the importance of cluster-specific insights, enhancing interpretability and offering practical value for buyers, sellers, and real estate analysts seeking more reliable property valuations.