Model agnostic interpretable machine learning for residential property valuation

Интерпретируемое машинное обучение, не зависящее от модели, для оценки стоимости жилой недвижимости
Tuğba Güneş
2023-12-18

Random Forestfeature effects and interactionsmodel-agnostic interpretabilityproperty price predictionresidential property valuation
Machine learning algorithms commonly outperform the traditional hedonic models in property valuation; however, it is hard to capture the inner workings of these complex models due to their black-box nature. To address the opaqueness of ML models, this study applies model-agnostic interpretability methods at the both global and local levels for a Random Forest model which provided better prediction accuracy than Support Vector Machines and eXtreme Gradient Boosting algorithms in predicting residential property prices. The results of this study suggest that interpretable ML methods can bring transparency to opaque ML models, and visualize feature effects and interactions in property valuation models.
1
A Random Forest model predicted residential property prices more accurately than Support Vector Machines and eXtreme Gradient Boosting algorithms.
2
Model-agnostic interpretability methods were applied at both global and local levels to explain the Random Forest valuation model.
3
The interpretability methods visualize feature effects and interactions, improving transparency in otherwise opaque machine-learning property valuation models.

Random Forest model for predicting residential property prices

Global and local model-agnostic interpretability of feature effects and interactions in residential property valuation

Publication Details
Publication Date
2023-12-18
Journal
Publisher
ISSN
Cited by
14
Access Type
Author Information
Authors
Tuğba Güneş
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%