Microburbs Research
Can GPT Pick Growth Suburbs?
We asked 7 versions of GPT to name Australia's top growth suburbs. Then we measured what actually happened over 38 months. Here is what we found.
You would have been better off picking suburbs at random.
Six of seven GPT versions picked suburbs that grew slower than the market average. Across all versions, GPT-picked suburbs underperformed by 0.35% per year. On a $1M property, that is $7,789 in lost equity compared to picking a suburb at random.
The Prompt We Used
We sent the same prompt to every version, for every state and territory in Australia:
What GPT-3.5 Said (NSW, up to 2024)
1. Parramatta - 20% growth: Parramatta is undergoing significant urban renewal and infrastructure development...
2. Penrith - 18% growth: Penrith is benefiting from its proximity to Sydney and ongoing investment in transport infrastructure.
3. Liverpool - 15% growth: Liverpool is experiencing population growth and improved amenities...
4. Castle Hill - 16% growth: Castle Hill is a popular suburb with strong demand...
... and so on for 100 suburbs per state.
Notice the generic reasoning. "Infrastructure development", "proximity to Sydney", "strong demand". These phrases appear thousands of times in real estate articles. GPT is reciting training text patterns, not analysing live market signals.
How Each Version Performed
Annualised outperformance or underperformance versus the market. Negative means you would have been better off picking suburbs at random.
What Happened to Investors Who Followed GPT?
GPT named its top picks. Here is what happened if you bought where it told you to, compared to the state average over the same period.
GPT's Worst Advice
$3.06M to $3.54M. Perth's most expensive suburb. On a $1M investment, you missed out on $454k compared to buying randomly in WA.
$2.57M to $2.78M. The famous lifestyle suburb barely moved. On $1M, you missed out on $398k compared to the Qld average.
$1.52M down to $1.20M. You lost real money while the rest of NSW grew. On $1M, you were $385k worse off.
$2.44M down to $1.88M. On $1M, you were $301k worse off than a random Victorian suburb.
Even a Broken Clock...
$259k to $715k. Massive outperformance. But GPT had no idea. It named the suburb but could not tell you why it would boom.
$426k to $826k. Beat the state by 33%. But the overall portfolio of GPT picks still lost to the market. One lucky pick does not make a strategy.
The Bottom Line
You would have been better off picking suburbs at random.
Across 6,888 scored predictions from 7 GPT versions, six underperformed the market. The only version that beat the market (GPT-4.1) did so by just 0.4% per year, gaining $3,302 on a $1M property over 9 months. That is not a strategy. That is noise.
At the other end, GPT-4.1-mini underperformed by 2.7% per year, costing investors $20,450 per $1M. GPT-4-turbo cost $15,915. GPT-4 cost $13,037. GPT-3.5 cost $11,504.
A random selection of suburbs in the same state would have outperformed GPT's recommendations in six of seven cases. Do not ask ChatGPT where to buy property.
Read the Full Research Whitepaper
All 7 GPT versions. All 8 states and territories. Animated growth charts. State-by-state breakdown. Data validation against CoreLogic and Domain.
Read the WhitepaperProperty Forecasting That Uses Real Data
Microburbs analyses 12.8 million data points across every suburb in Australia. Not text predictions. Actual supply, demand, and price signals updated weekly.