Can an algorithm predict which businesses will close?

A closed store in New York City. Image: Getty.

Over the past decade, changes in the way people shop have led more and more businesses to close their doors, from small music venues to book shops and even major department stores. This trend has been attributed to several factors, including a shift towards online shopping and changing spending preferences. But business closures are complex, and often due to many intertwined factors.

To better understand and account for some of these factors, my colleagues at the University of Cambridge and Singapore Management University and I built a machine learning model, which predicted shop closures in ten cities around the world with 80 per cent accuracy.

Our research modelled how people move through urban areas, to predict whether a given business will close down. This research could help city authorities and business owners to make better decisions, for example about licensing agreements and opening hours.

Pattern spotting

Machine learning is a powerful tool which can automatically identify patterns in data. A machine learning model uses those patterns to tests hypotheses and make predictions. Social media provides a rich source of data to examine the patterns of its users through their posts, interactions and movements. The detail in these datasets can help researchers to build robust models, with a complex understanding of user trends.

Using data about consumer demand and transport, along with ground-truth data on whether businesses actually closed, we devised metrics which our machine learning model used to identify patterns. We then analysed how well this model predicted whether a business would close, given only metrics about that business and the area it was in.

Our first dataset was from Foursquare, a location recommendation platform, which included check-in details of anonymous users and represented the demand for businesses over time. We also used data from taxis trajectories, which gave us the pickup and drop-off points of thousands of anonymous users; these represented dynamics of how people move between different areas of a city. We used historic data from 2011 to 2013.

Taxiiii! Image: Sunset Noir/Flickr/creative commons.

We looked at a few different metrics. The neighbourhood profile took into account the area surrounding a business, such as the different kinds of businesses also operating, as well as competition. Customer visit patterns represented how popular a business was at any given time of day, compared with its local competitors. And business attributes defined basic properties such as the price bracket and type of business.

These three metrics enabled us to model how closure predictions differ between new and established venues, how the predictions varied across cities and which metrics were the most significant predictors of closure. We were able to predict the closure of established businesses more accurately, which suggested that new businesses can face closure from a bigger variety of causes.


Making predictions

We found that different metrics were useful for predicting closures in different cities. But across the ten cities in our experiment – Chicago, London, New York, Singapore, Helsinki, Jakarta, Los Angeles, Paris, San Fransciso and Tokyo – we saw that three factors were almost always significant predictors of a business’s closure.

The first important factor was the range of time during which a business was popular. We found that businesses which cater to only specific customer segments – for example, a café popular with office workers at lunchtime – are more likely to close. It also mattered when a business was popular, compared with its competitors in the neighbourhood. Businesses that were popular outside of the typical hours of other businesses in the area tended to survive longer.

We also found that when the diversity of businesses declined, the likelihood of closure increased. So businesses located in neighbourhoods with a more diverse mix of businesses tended to survive longer.

Of course, like any dataset, the information we used from Foursquare and taxis is biased in some ways, as the users may be skewed towards certain demographics or check in to some types of businesses more than others. But by using two datasets which target different kinds of users, we hoped to mitigate those biases. And the consistency of our analysis across multiple cities gave us confidence in our results.

We hope that this novel approach to predicting business closures with highly detailed datasets will help reveal new insights about how consumers move around cities, and inform the decisions of business owners, local authorities and urban planners right around the world.

The Conversation

Krittika D'Silva, PhD Candidate, University of Cambridge.

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

 
 
 
 

So why is Peterborough growing so quickly?

Peterborough Cathedral. Image: Jules & Jenny/Flickr/creative commons.

The latest instalment of our series, in which we use the Centre for Cities’ data tools to crunch some of the numbers on Britain’s cities.  

The 2001 census put the population of Peterborough at 156,000. Some time before next spring, it’s projected to pass 200,000. That, for those keeping score, is an increase of about 28 per cent. Whether this makes it the fastest growing city in Britain or merely the second or the fourth – the vagueness of Britain’s boundaries means that different reports reach different conclusions – doesn’t really matter. This is a staggering rate of growth.

Oh, and since austerity kicked in, the city council has had its grant from central government cut by 80 percent.

Expansion on this scale and at this rate is the sort of thing that’d have a lot of councils in our NIMBY-ish political culture breaking out in hives; that seems to go double for Tory-run ones in Leave-voting areas. This lot, though, seem to be thriving on it. “I think the opportunity in Peterborough is fantastic,” says Dave Anderson, the city’s interim planning director. “We’re looking at growing to 235,000 by the mid-2030s.”

More striking still is that the Conservative council leader John Holdich agrees. “I’m a believer in ‘WIMBY’: what in my back yard?” he says. He’s responsible, he says, not just to his electorate, but “to our future kids, and grandkids” too – plus, at that rate of growth, a lot of incomers, too.

All this raises two questions. Why is Peterborough growing so quickly? And what can it do to prepare itself?

If you’re a little uncertain exactly where Peterborough is, don’t worry, you’re in good company. Until 1889, the “Soke of Peterborough” was an unlikely east-ward extrusion from Northamptonshire, far to its south west. Then it was a county in its own right; then part of the now-defunct Huntingdonshire. Today it’s in Cambridgeshire, with which it shares a metro mayor, the Conservative James Palmer. When I ask Holdich, who’s giving me a whistlestop tour of the city’s cathedral quarter, to explain all this, he just shrugs. “They keep moving us about.”

Sitting on the edge of the Fens, Peterborough is, officially, a part of the East of England region; but it’s just up the road from East Midlands cities including Leicester and Nottingham. I’d mentally pigeonholed it as a London-commuter town, albeit a far flung one; but when I actually looked it up, I was surprised to discover it was closer to Birmingham (70 miles) than London (75), and halfway up to Hull (81).


The more flattering interpretation of all this is that it’s on a bit of a crossroads: between capital and north, East Anglia and the Midlands. On the road network, that’s literally true – it’s where the A1 meets the A47, the main east-west road at this latitude – and railway lines extend in all directions, too.

All of which makes Peterborough a pretty nifty place to be if you’re, say, a large logistics firm.

This has clearly contributed to the city’s growth. “It has access to lots of land and cheaper labour than anywhere else in the Greater South East,” says Paul Swinney, director of policy at the Centre for Cities. “Those attributes appeal to land hungry, low-skilled business as opposed to higher-skilled more knowledge-based ones.”

That alone would point to a similar economy to a lot of northern cities – but there’s another thing driving Peterborough’s development. Despite being 70 miles from the capital, the East Coast Main Line means it’s well under an hour away by train.

In 1967, what’s more, the ancient cathedral city was designated a new town, to house London’s overspill population. The development corporation which owned the land and built the new town upon it, evolved into a development agency; today the same role is played by bodies like Opportunity Peterborough and the Peterborough Investment Partnership.

The city also offers relatively cheap housing: you can get a four-bed family home for not much over £200,000. That’s fuelled growth further as London-based workers scratch around for the increasingly tiny pool of places that are both commutable and affordable.

The housing affordability ratio shows average house prices as a multiple of average incomes. Peterborough is notably more affordable than Cambridge, London and the national average. Image: Centre for Cities data tool.

It’s made it attractive to service businesses, too. “London has probably played quite a big role in the city’s development,” says Swinney. “If you don’t want to move too far out, it’s probably one of the cheapest places to move to.”

The result of all this is that it has an unusually mixed economy. There’s light industry and logistics, in the office and warehouse parks that line the dual-carriageways (“parkways”) of the city. But there are also financial services and digital media companies moving in, bringing better paying jobs. In a country where most city economies are built on either high value services or land-hungry warehousing businesses, Peterborough has somehow managed to create a mixed economy.

Peterborough’s industrial profile: more services and less manufacturing, and more private and fewer public sector jobs, than the national average. Image: Centre for Cities.

At the moment, if people think of Peterborough at all, they’re likely to imagine a large town, rather than the fair-size regional city it’s on course to become. Its glorious 12th century cathedral – the hallmark of an ancient city, and at 44m still by far the highest spot on the horizon for miles around – is stunning. But it’s barely known to outsiders, and at least twice on my tour, the council’s communications officer proudly announces that the Telegraph named her patch as one of the best towns to live in within an hour of London, before adding, “even though we’re a city”. 

So part of the council’s current mission is to ensure that Peterborough has all the amenities people would expect from a settlement on this scale. “What the city needs to do is to adopt the mind-set of a slightly larger city,” says Anderson. Slightly smaller Swansea is developing a new music arena, of the sort Peterborough doesn’t have and needs. He frets, too, about retail spend “leaking” to Cambridge or Leicester. “Retail is now seen as a leisure activity: in the core of the city it’s important that offer is there.”

To that end, the early 1980s Queensgate shopping centre is being redeveloped, with John Lewis giving up a chunk of space to provide a new city centre cinema. (At present, the area only has road-side suburban multiplexes.) There’s major office, retail and housing development underway at North Westgate, as well as work to improve the walking route between the station and the commercial centre, in a similar manner to Coventry.

Fletton Quays. Image: Peterborough Investment Partnership.

Then there’s the city’s underused riverside. The council recently moved to new digs, in Fletton Quays, on the far bank of the River Nene from the centre. Across the river from the Embankment, the city centre’s largest green space, it’s a pretty lovely spot, of the sort where one might expect riverside pubs or restaurants with outdoor seating – but at the moment the space is largely empty. The Fletton Quays development will change all that, bringing more retail space and yes, new homes, too.

Jobs in Peterborough are unusually distributed around town: in many cities, most jobs are in the central business district. Image: Centre for Cities.

The big thing everyone agrees is missing, though, is a university. It already has the University Centre Peterborough, where degrees are provided by Anglia Ruskin University. The plan is for the site – a joint venture between ARU and Peterborough Regional College – to go its own way as an independent institution, the University of Peterborough, in autumn 2022. That should help provide the skills that the city needs to grow. A growing student population should also bring life and cash to the city centre. 

How big could Peterborough get? Could its enviable combination of good location and cheap housing and grand ambitions combine to make it the modern equivalent of Manchester or Liverpool – one of the great cities of the 21st century?

Well, probably not: “I think the optimum size for a city is probably about 250,000,” says Holdich. But that’s still a whole quarter bigger than now, and the council leader even discusses the possibility of refitting his dual-carriageway-based-city with some kind of light rail network to service that growing population. Peterborough’s not done growing yet.

Jonn Elledge is the editor of CityMetric. He is on Twitter as @jonnelledge and on Facebook as JonnElledgeWrites.

Want more of this stuff? Follow CityMetric on Twitter or Facebook.