sign up log in
Want to go ad-free? Find out how, here.

Use of AI in property valuation is on the rise – but we need greater transparency and trust

Technology / news
Use of AI in property valuation is on the rise – but we need greater transparency and trust

By William Cheung & Edward Yiu*

New Zealand’s economy has been described as a “housing market with bits tacked on”. Buying and selling property is a national sport fuelled by the rising value of homes across the country.

But the wider public has little understanding of how those property valuations are created – despite their being a key factor in most banks’ decisions about how much they are willing to lend for a mortgage.

Automated valuation models (AVM) – systems enabled by artificial intelligence (AI) that crunch vast datasets to produce instant property values – have done little to improve transparency in the process.

These models started gaining traction in New Zealand in the early 2010s. The early versions used limited data sources like property sales records and council information. Today’s more advanced models include high-quality geo-spatial data from sources such as Land Information New Zealand.

AI models have improved efficiency. But the proprietary algorithms behind those AVMs can make it difficult for homeowners and industry professionals to understand how specific values are calculated.

In our ongoing research, we are developing a framework that evaluates these automated valuations. We have looked at how the figures should be interpreted and what factors might be missed by the AI models.

In a property market as geographically and culturally varied as New Zealand’s, these points are not only relevant — they are critical. The rapid integration of AI into property valuation is no longer just about innovation and speed. It is about trust, transparency and a robust framework for accountability.

AI valuations are a black box

In New Zealand, property valuation has traditionally been a labour-intensive process. Valuers would usually inspect properties, make market comparisons and apply their expert judgement to arrive at a final value estimate.

But this approach is slow, expensive and prone to human error. As demand for more efficient property valuations increased, the use of AI brought in much-needed change.

But the rise of these valuations models is not without its challenges. While AI offers speed and consistency, it also comes with a critical downside: a lack of transparency.

AVMs often operate as “black boxes”, providing little insight into the data and methodologies that drive their valuations. This raises serious concerns about the consistency, objectivity and transparency of these systems.

What exactly the algorithm is doing when an AVM estimates a home’s value is not clear. Such opaqueness has real-world consequences, perpetuating market imbalances and inequities.

Without a framework to monitor and correct these discrepancies, AI models risk distorting the property market further, especially in a country as diverse as New Zealand, where regional, cultural and historical factors significantly influence property values.

Transparency and accountability

A recent discussion forum with real estate industry insiders, law researchers and computer scientists on AI governance and property valuations highlighted the need for greater accountability when it comes to AVMs. Transparency alone is not enough. Trust must be built into the system.

This can be achieved by requiring AI developers and users to disclose data sources, algorithms and error margins behind their valuations.

Additionally, valuation models should incorporate a “confidence interval” – a range of prices that shows how much the estimated value might vary. This offers users a clearer understanding of the uncertainty inherent in each valuation.

But effective AI governance in property valuation cannot be achieved in isolation. It demands collaboration between regulators, AI developers and property professionals.

Bias correction

New Zealand urgently needs a comprehensive evaluation framework for AVMs, one that prioritises transparency, accountability and bias correction.

This is where our research comes in. We repeatedly resample small portions of the data to account for situations where property value data do not follow a normal distribution.

This process generates a confidence interval showing a range of possible values around each property estimate. Users are then able to understand the variability and reliability of the AI-generated valuations, even when the data are irregular or skewed.

Our framework goes beyond transparency. It incorporates a bias correction mechanism that detects and adjusts for constantly overvalued or undervalued estimates within AVM outputs. One example of this relates to regional disparities or undervaluation of particular property types.

By addressing these biases, we ensure valuations that are not only accountable or auditable but also fair. The goal is to avoid the long-term market distortions that unchecked AI models could create.

The rise of AI auditing

But transparency alone is not enough. The auditing of AI-generated information is becoming increasingly important.

New Zealand’s courts now require a qualified person to check information generated by AI and subsequently used in tribunal proceedings.

In much the same way financial auditors ensure accuracy in accounting, AI auditors will play a pivotal role in maintaining the integrity of valuations.

Based on earlier research, we are auditing the artificial valuation model estimates by comparing them with the market transacted prices of the same houses in the same period.

It is not just about trusting the algorithms but trusting the people and systems behind them.The Conversation


*William Cheung, Senior Lecturer, Business School, University of Auckland, Waipapa Taumata Rau and Edward Yiu, Associate Professor, School of Business, University of Auckland, Waipapa Taumata Rau.

This article is republished from The Conversation under a Creative Commons license. Read the original article.

We welcome your comments below. If you are not already registered, please register to comment.

Remember we welcome robust, respectful and insightful debate. We don't welcome abusive or defamatory comments and will de-register those repeatedly making such comments. Our current comment policy is here.

11 Comments

The AI valuations can also be quite misleading, with many updated at a different level by the real estate agent right before the property goes live on the market.  Most wouldn't notice the extra "agent appraised" wording that appears alongside, and only appearing for a short time.

Up
4

Here I have a classic example, sold for 1.2m in dec 21 then went back on the market a few months back, agent appraised at 1.9m and homes has kept it at that value, totally crazy.

https://homes.co.nz/address/whangarei/kamo/5-st-andrews-place/Gjq2X

Up
3

The value graph on that one is gob-smacking - and I think people will notice gigantic bumps in valuations when the house is being sold.

If you look back through the sales history, it was valued at 2 million in 2021 - but sold for 1.2 (the only valuation that actually matters). The agents aren't exactly subtle, are they?

Up
3

Isn't it about time A.I. was used to reduce the profits of our banks?

I mean, seriously, the bulk of the work to hand out mortgages simply doesn't justify the profits the banks make off them. Ditto the bulk of transactional banking.

Up
3

AI or for that matter any other other tech will not reduce the profits for banks, its cost will only be used to justify more profits, and be used to sell us more stuff.

Think about how far technology has come, how much less effort it is to do a transaction than 50 years ago, they had to have a person do every single one of them, but instead they are getting more money than ever.

Think about how long it took them to get 24/7 transactions (decades and still not done right), How long it has taken them to implement name validation on account transfers, I am a technical person (and worked in a banks IT department) and it is simple.

Up
0

Maybe we should address the root cause and stop "the rising value of homes across the country"?

Just saying ...

Up
7

William and Edward are saying the A.I. models are getting it wrong. And we'd all agree?

But what happens when they evolve and they get it consistently right?
Will we need more than one of them?
Will we even need auctioneers or real estate agents?
Especially so if houses ceased to be part of the financial system ....???

(fyi: i've been playing around with getting A.I. to analyse the bathroom & kitchen pictures on listings. Tricky.)

Up
0

Houses not part of the financial system you say? Like the UK's dystopian housing estates or Soviet apartment blocks?

Up
0

Maybe Auckland Council should be using AI to do our valuations.....   they are delayed until early next year, meanwhile OneLonelyWoof thinks Auckland is down 4% from peak.....   Tell em they are dreamin

 

Up
1

I could teach an average 16 to 18 year old to competently drive a car in a few weeks. It would probably take several years to each the average 16 to 18 year old to do my job. AI can't competently do either yet despite massive investment in just learning that one skillset.

 

We have to be realistic that any commercial deployment of AI to tasks with any level of complexity will take a long, long time.

Up
0

I am a fan of a buyers appraisal AI as I think currently there is too much incentive to make it good for REAs and vendors, leading to a conflict of interest.

With ML AI you want to "wrangle" the data into nice clean features before you send it through the model, for transparency it could be nice to see the data features for any given valuation, but that is in many ways the proprietary special sauce of the company making the AI. Perhaps giving LINZ a mandate to generate some kind of common, public, feature-set for properties would be beneficial. The most beneficial feature would be the square meter valuation on land based on recent nearby sales and that could be a great tool if the government ever wants to bring back LVTs. It could also give councils the ability to have a regular ratings valuations.

SKF

Up
2