Comparing automated valuation models for real estate assessment in the Santiago Metropolitan Region: A study on machine learning algorithms and hedonic pricing with spatial adjustments

Сравнение автоматизированных моделей оценки недвижимости в Столичном регионе Сантьяго: исследование алгоритмов машинного обучения и гедонического ценообразования с пространственными корректировками
Jocelyn Tapia, Nicolas Chavez-Garzon, Raúl Pezoa, Paulina Suarez-Aldunate, Mauricio Pilleux
2025-03-25

LightGBMSHAPautomated valuation modelsconvolutional neural networksspatial autoregressive model
This study compares the precision and interpretability of two automated valuation models for evaluating the real estate market in the Santiago Metropolitan Region of Chile: machine learning algorithms, specifically LightGBM, and hedonic prices with spatial adjustments (SAR). Traditional residence attributes, such as housing amenities and proximity to services, were considered alongside visual information extracted from images using Convolutional Neural Networks (CNN). The research evaluates the influence of each model characteristic on performance metrics and identifies the relative importance of attributes using the SHapley Additive exPlanations (SHAP) algorithm. The results demonstrate the positive impact of image-based variables on performance metrics, showing that the introduction of visual information can considerably reduce error margins when estimating housing prices. In addition, the SHAP algorithm reveals complex non-linear interactions between price and crucial variables such as total surface area and neighborhood attributes, highlighting the importance of using methods that can capture these effects. Likewise, both LightGBM and SAR models indicate that variables that have the most significant impact on the value of properties are total surface area, municipality quality index, average academic level of nearby schools, and the number of bathrooms.
1
Both LightGBM and SAR identify total surface area, municipality quality, nearby schools’ average academic level, and bathroom count as the most influential valuation variables.
2
Combining traditional housing attributes with CNN-extracted visual information considerably reduces housing-price estimation errors.
3
SHAP analysis identifies complex nonlinear interactions involving total surface area, neighborhood characteristics, and property prices.
4
The findings support valuation methods capable of incorporating visual data and modeling spatial and nonlinear effects.
5
The study compares LightGBM machine-learning models with spatially adjusted hedonic pricing models (SAR) for property valuation in Santiago, Chile.

Residential properties and the real estate market in the Santiago Metropolitan Region of Chile

The precision, interpretability, variable importance, and nonlinear effects of automated property valuation models using traditional, spatial, and image-based attributes

Publication Details
Publication Date
2025-03-25
Journal
Publisher
ISSN
Cited by
15
Access Type
Author Information
Authors
Jocelyn Tapia
Nicolas Chavez-Garzon
Raúl Pezoa
Paulina Suarez-Aldunate
Mauricio Pilleux
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%