Forget chicken shops vs. coffee shops. Stop stalking Waitrose location scouts. All you need to scientifically predict the next up and coming area is a bit of social media.

Well, actually, a lot of social media, and some data mapping software, but still, with these tools you can get in long before the Ocado delivery vans arrive.

So say the University of Cambridge-led team behind a study presented this April at the International World Wide Web Conference in Montreal.

The researchers used data from more than 37,000 regular Twitter and Foursquare users and 42,000 venues in London to quantify the “social diversity” of areas in the capital and correlated this with government data on the locations’ relative prosperity in 2010 and 2015.

“We understand that people who diversify their contacts not only socially but also geographically have high social capital but what about places?” said Desislava Hristova from the University’s Computer Laboratory, and the study’s lead author.

“We all have a general notion of the social diversity of places and the people that visit them, but we’ve attempted to formalise this – it could even be used as a specialised local search engine.”

Venues that tended to gather a wider variety of random strangers were more diverse than those acting as a place for friends to meet at regularly. Types of location that fitted the former category included arts venues, pubs and bars, public transport and parks, while those in the latter category included places of worship, residences, primary schools and strip clubs.

Friends were also more likely to meet at fast food joints and hookah bars, while strangers were more likely to sit alongside each other at dumpling restaurants and gay bars.

The study found that the most socially homogenous areas tended to be either very rich or very poor (both Kensington & Chelsea and Barking & Dagenham were not socially diverse despite being at opposite ends of the wealth scale) with inward-looking, tightly knit neighbourhoods keeping resources within the community and resisting change.

In contrast, the key marker for identifying a gentrifying area was a combination of high social diversity and high deprivation levels.

Unsurprisingly, Hackney provided a near perfect model for the research. In 2010, the borough had both the highest social diversity and the second highest deprivation in London. By 2015, it had seen the greatest improvement on the deprivation scale, shown by soaring house prices and decreasing crime rates, whilst retaining its diverse population.

Other boroughs that were pinpointed as showing signs of gentrification included Tower Hamlets, Greenwich and Lambeth.

Although showing a less dramatic increase in prosperity (presumably because it had less far to go in the first place), Camden ranked as one of the boroughs with the highest diversity, while still having fairly high levels of deprivation, making it another prime candidate for gentrification in the same period.

This is borne out by average property sales prices in the borough, which rose 64 per cent from £504,821 in January 2010, to £826,399 five years later.

The paper’s authors believe this method stands out from existing analysis for its ability to predict gentrification before it happens. They hope the model will be used by urban planners to anticipate some of the damaging gentrification effects, while harnessing the good ones, but it could just as easily be used by canny property buyers hoping to beat the flat white brigade at their own game.