Moving beyond valuation as a matter of professional judgment and historical comparability, artificial intelligence is reshaping property valuation in South Africa by combining trusted data, machine learning and human expertise to generate faster and more accurate results.
The scale and depth of the underlying data matters when using AIVM, Lightstone's AI-powered tool used for residential property valuations, because valuation models are only as strong as the information they learn from.
“By combining deeds records, cadastral data, municipal rolls, listing data, point-of-interest information and imagery, Lightstone’s system creates a much richer view of property value than traditional methods alone,” said Hayley Ivins-Downs, Managing Executive Real Estate, Lightstone Property, at The Africa Valuation Conference 2026 recently.
In a presentation titled “Our journey and applications of AI in AIVM”, Ivins-Downs explained how Lightstone's data includes nationwide coverage of registered South African properties, millions of indexed properties and street addresses, and decades of working transaction history.
data assets
Ivins-Downs said AIVM used features such as a property's location, size, past sales prices and other structured inputs to estimate market value.
To make the output useful to decision makers, AIVM includes a confidence score and a safety score, which helps users not only understand the estimate but also how much confidence to have in it. The emphasis on explainability was important because it kept the model transparent rather than turning it into a black box.
the outcome? It provides market insights that track property price inflation, monitor property transfer activity and days on market, highlight the percentage of prices achieved in different areas, and merge proprietary data across the property, automotive and retail sectors to create a competitive advantage.
Ivins-Downs stressed that AI should support, not replace, human experts, and he highlighted “human-in-the-loop” decision making, where models assist analysts, appraisers and lenders while leaving room for professional oversight.
Ivins-Downs said Lightstone is empowering the asset and financial ecosystem through explainable intelligence, around three pillars:
- Transparency: Unlike typical “black box” systems, Lightstone’s AI provides “white box benefit” predictions that can be interrogated and understood by human decision makers.
- Integrity: Lightstone is Africa's only member of the European AVM Alliance and meets strict global standards for statistical rigor and independence. Additionally, Lightstone’s “Narrow AI” is trained on South African nuances, interpreting action logs, municipal data gaps and informal market anomalies that typical models miss.
- The results: banking efficiency (including immediate “lending-grade” market value at the offer-to-purchase stage, leading to higher deal approval rates and less friction in bond origination), and strategic accuracy.
Lightstone is also exploring computer vision, satellite imagery and other advanced technologies to improve coverage and accuracy.
Overall, Ivins-Downs said AI is a practical tool for the property and financial sectors, not just a technological experiment. Its message is that the future of evaluation depends on reliable data, continuous model improvement, and the ability to clearly explain results.
