313. Establishing a Modern Approach to Property Valuation in the Public Sector
Invited abstract in session MC-49: Analytics and the link with stochastic dynamics 1, stream Analytics.
Monday, 12:30-14:00Room: Parkinson B10
Authors (first author is the speaker)
| 1. | Andy Grayson
|
| Valuation Analytics, Valuation Office Agency |
Abstract
The Valuation Office Agency (VOA) plays a pivotal role in determining property values for Council Tax Bands, generating billions of pounds for local authorities. In response to Welsh Government's decision to re-band Council Tax for the first time in two decades, a multi-disciplinary team of operational researchers and statisticians joined forces with expert valuers to create a cutting-edge valuation modelling function. This initiative saw the introduction of predictive models, known as Automated Valuation Models (AVM), in a model-assisted approach to accurately estimate current house prices and re-band properties. External experts have validated our approach, praising its novel structure and reliability.
This presentation will explore:
The series of models that comprise the AVM, including the groundbreaking Gaussian Markov Random Field approach for assessing the impact of location.
Our development of a comprehensive suite of tools and processes that empower valuers to validate and adjust these valuations.
The challenges faced and lessons learned from a comprehensive dry run, along with our plans for future enhancements.
Through collaboration of interdisciplinary expertise, our team has successfully integrated these advanced models into the valuation process, providing a robust framework for property assessment. Looking ahead, we are committed to continuous improvement and innovation, to refine and improve our models further.
Keywords
- Analytics and Data Science
- OR/MS and the Public Sector
- Machine Learning
Status: accepted
Back to the list of papers