On the Performance of LLMs for Real Estate Appraisal

2025-06-13

AI Summary

Persistent information asymmetry in real estate markets undermines appraisal transparency and public accessibility. To address this, we propose an LLM-enhanced framework for interpretable house price prediction. Our method innovatively integrates feature similarity and geographic proximity for context example selection; introduces market-report augmentation and hybrid prompting strategies that incorporate hedonic pricing variables to enable structured reasoning; and—first in the literature—systematically validates the alignment between LLM-generated self-explanations and conclusions from conventional econometric models, thereby enhancing model credibility. Evaluated across multi-country datasets, our approach achieves predictive accuracy comparable to state-of-the-art traditional models while substantially improving interpretability. Experimental results confirm that prompt optimization significantly boosts performance; however, they also expose inherent LLM limitations in price-range calibration and spatial reasoning.

Technology Category

• Machine Learning: Transparent, Interpretable, Explainable ML
• Search and Optimization: Learning to Search
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

The real estate market is vital to global economies but suffers from significant information asymmetry. This study examines how Large Language Models (LLMs) can democratize access to real estate insights by generating competitive and interpretable house price estimates through optimized In-Context Learning (ICL) strategies. We systematically evaluate leading LLMs on diverse international housing datasets, comparing zero-shot, few-shot, market report-enhanced, and hybrid prompting techniques. Our results show that LLMs effectively leverage hedonic variables, such as property size and amenities, to produce meaningful estimates. While traditional machine learning models remain strong for pure predictive accuracy, LLMs offer a more accessible, interactive and interpretable alternative. Although self-explanations require cautious interpretation, we find that LLMs explain their predictions in agreement with state-of-the-art models, confirming their trustworthiness. Carefully selected in-context examples based on feature similarity and geographic proximity, significantly enhance LLM performance, yet LLMs struggle with overconfidence in price intervals and limited spatial reasoning. We offer practical guidance for structured prediction tasks through prompt optimization. Our findings highlight LLMs' potential to improve transparency in real estate appraisal and provide actionable insights for stakeholders.

Problem

• LLMs for democratizing real estate price insights
• Evaluating LLMs on diverse housing datasets
• Enhancing LLM performance with optimized prompting

Innovation

• Optimized In-Context Learning for house price estimates
• Hybrid prompting techniques enhance LLM performance
• Feature similarity and geographic proximity improve accuracy