Invest
This robot can ‘predict wealth’ from outer space
If you could design the “perfect city”, what would this city look like from space?
This robot can ‘predict wealth’ from outer space
If you could design the “perfect city”, what would this city look like from space?
That’s the question that fuelled the creation of “Penny”, an artificial intelligence (AI) platform that can “predict wealth” from space.
Penny uses data from the US census, expertise from Carnegie Mellon and visualisations and high-res images from Stamen Design and DigitalGlobe to predict the wealth of different regions within virtual cityscapes.
Currently, Penny has analysed New York City and St. Louis.
Writing for the World Economic Forum, Jeff Tarr, the CEO of DigitalGlobe said Penny could “make cities smarter than is humanly possible”.
“We’re already using machines to make sense of the world as it is; the possibility before us is that machines help us create a world as it should be and have us question the nature of the thinking behind its design.”
He explained that Penny has been taught to recognise “with uncanny accuracy” the patterns of neighbourhood wealth, like the number of trees, brownstone buildings, car parks and freeways by running census data against the satellite imagery.
“It does more, though,” he continued.
“You don’t just extract information from this tool, but interact with it, using a compelling, human-centred interface. Drop a grove of trees into the middle of Harlem to see the neighbourhood’s virtual income level rise or fall.”
For example, Penny reads the Bronx area as being of a low median income bracket. Add the Empire State building and the income grows to medium-low.
Correspondingly, the area around the prestigious Plaza Hotel and Central Park drops from a high median income bracket to medium-low once a parking lot is added. Add another two parking lots and the area just up the road from Trump Tower drops to the low median income bracket.
“The basic evaluations are logical,” said Mr Tarr.
“More parks commonly indicate higher income; more parking lots, lower. But its results are not always intuitive: if you add two trees to a neighbourhood, you may not see a difference, but the third might be a tipping point. It’s not just about the urban features you add, it’s the features and the context into which they’re placed.”
Mr Tarr said that while Penny can’t yet say what the perfect city looks like, it raises a number of questions like: “What sorts of problems, even aesthetic ones, can we solve by partnering with new kinds of intelligence – and what will it take to get there?”
And: “Will we bristle at machine-told truths that violate our preconceptions about value or lifestyle? Does human emotion hinder or help our decision making?”
However, Mr Tarr argued that Penny’s real value lies in the way it can uncover unconscious biases or uncomfortable truths. Questioning whether Penny can “recognise and respect the boundaries and symbols that are so meaningful to us”, Mr Tarr said Penny could instead highlight a truth that humans are unable to see.
“The most compelling questions don’t come when that [AI] lens is turned outward – at our cities – but when it is turned directly at us.”
RELATED ARTICLES
Property
From intuition to instrumentation: How a "two-stakeholder" sales playbook lifted close rates and cut cycle times
High-stakes consumer purchases are increasingly joint decisions. When one partner is under-served, deals stall. This case study follows an Australian real estate group that rebuilt its sales motion ...Read more
Property
Selling in 2025: How to spot bad agents fast—and build an ROI-first vendor playbook
In Australia’s property market, choosing the wrong listing agent isn’t just inconvenient—it’s a textbook principal–agent failure that can wipe tens of thousands off your sale outcomeRead more
Property
Selling in 2026: How to de‑risk your agent choice and protect tens of thousands at settlement
Choosing the wrong selling agent isn’t just an inconvenience — it’s a balance‑sheet risk. In a market where digital discovery is concentrated and AI is recasting how listings are priced and promoted, ...Read more
Property
Rate resilience in Australian housing: why scarce supply is overpowering monetary tightening
Australia’s housing market is defying higher borrowing costs because the binding constraint isn’t demand—it’s supply. Brokers report persistent buyer competition and investor repositioning, while ...Read more
Property
Victoria’s $100m renter support push: what it means for landlords, proptech and the housing economy
Victoria has unveiled a new suite of rental support services, including a dedicated helpline for renters aged 55+, underpinned by a funding package widely reported at around $100 millionRead more
Property
The multigenerational home moves mainstream: where the next margin lives in Australian real estate
Multigenerational living is shifting from edge case to core demand driver in Australia’s housing market. For agents, developers and lenders, the commercial upside lies in rethinking product design, ...Read more
Property
Multigenerational living is moving mainstream: how agents, developers and lenders can monetise the shift
Australia’s quiet housing revolution is no longer a niche lifestyle choice; it’s a structural shift in demand that will reward property businesses prepared to redesign product, pricing and ...Read more
Property
Prestige property, precision choice: a case study in selecting the right agent when millions are at stake
In Australia’s top-tier housing market, the wrong agent choice can quietly erase six figures from a sale. Privacy protocols, discreet buyer networks and data-savvy marketing have become the new ...Read more
Property
From intuition to instrumentation: How a "two-stakeholder" sales playbook lifted close rates and cut cycle times
High-stakes consumer purchases are increasingly joint decisions. When one partner is under-served, deals stall. This case study follows an Australian real estate group that rebuilt its sales motion ...Read more
Property
Selling in 2025: How to spot bad agents fast—and build an ROI-first vendor playbook
In Australia’s property market, choosing the wrong listing agent isn’t just inconvenient—it’s a textbook principal–agent failure that can wipe tens of thousands off your sale outcomeRead more
Property
Selling in 2026: How to de‑risk your agent choice and protect tens of thousands at settlement
Choosing the wrong selling agent isn’t just an inconvenience — it’s a balance‑sheet risk. In a market where digital discovery is concentrated and AI is recasting how listings are priced and promoted, ...Read more
Property
Rate resilience in Australian housing: why scarce supply is overpowering monetary tightening
Australia’s housing market is defying higher borrowing costs because the binding constraint isn’t demand—it’s supply. Brokers report persistent buyer competition and investor repositioning, while ...Read more
Property
Victoria’s $100m renter support push: what it means for landlords, proptech and the housing economy
Victoria has unveiled a new suite of rental support services, including a dedicated helpline for renters aged 55+, underpinned by a funding package widely reported at around $100 millionRead more
Property
The multigenerational home moves mainstream: where the next margin lives in Australian real estate
Multigenerational living is shifting from edge case to core demand driver in Australia’s housing market. For agents, developers and lenders, the commercial upside lies in rethinking product design, ...Read more
Property
Multigenerational living is moving mainstream: how agents, developers and lenders can monetise the shift
Australia’s quiet housing revolution is no longer a niche lifestyle choice; it’s a structural shift in demand that will reward property businesses prepared to redesign product, pricing and ...Read more
Property
Prestige property, precision choice: a case study in selecting the right agent when millions are at stake
In Australia’s top-tier housing market, the wrong agent choice can quietly erase six figures from a sale. Privacy protocols, discreet buyer networks and data-savvy marketing have become the new ...Read more
