Comparison of expert algorithms with machine learning models for real estate appraisal
Сравнение экспертных алгоритмов с моделями машинного обучения для оценки недвижимости
2017-07-01
SCID: 54.1/awgad7vk
Discuss with AI
expert algorithmsmachine learning modelsproperty valuationreal estate appraisalsales comparison approach
Figures from the paper
Abstract (AI)
Machine learning models require numerous training examples to provide reliable predictions of real estate prices. Expert algorithms could be applied wherever only several training samples are available. The accuracy of two expert algorithms based on the sales comparison approach was experimentally examined using real-world data derived from a cadastral system and registry of real estate transactions. The performance of the algorithms was compared with three data driven regression models for property valuation. Statistical analysis of the obtained results was conducted.
Key Findings
1
Expert algorithms are positioned as suitable alternatives when only a small number of training samples is available.
2
The abstract does not report specific accuracy results or identify a superior algorithm.
3
The algorithms were tested using real-world data from a cadastral system and a real estate transaction registry.
4
The study experimentally evaluates two expert algorithms based on the sales comparison approach for real estate price appraisal.
5
Their valuation performance was compared with three data-driven regression models using statistical analysis.
Research Object
real estate property valuation using transaction and cadastral data
Research Subject
comparative accuracy and predictive performance of expert algorithms versus machine-learning regression models under limited training data
Publication Details
Publication Date
2017-07-01
Journal
Publisher
ISSN
Cited by
46
Access Type
Author Information
Download PDF
Subscribe to digest