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.

 
 
 
 

Cycling on London’s Euston Road is still a terrifying experience

Cyclists on the Euston Road. Image: Jonn Elledge.

The New Road, which skirted the northern boundaries of London’s built up area, first opened in the 1750s. Originally, it was intended to link up outlying villages and provide a route to drive sheep and cows to the meat market at Smithfield without having to pass through the congested city centre. 

As with bypasses and ring roads the world over, however, it increasingly became congested in its own right. Today, you won’t often find livestock on the route, which is now Marylebone, Euston and City roads. But you will find up to six lanes of often stationary buses, cabs, and private vehicles. In a city whose centre is largely free of multi-lane highways, London’s northern ring road has long been the sort of abomination that you avoid at all costs.

But now, somewhat surprisingly, the road is seeing yet another new use. Earlier this week, the first phase of a temporary cycle lane opened on the Euston Road, the middle section of the route which runs for roughly a mile. As London rethinks roads throughout the city, this addition to the cycling map falls solidly into the category of streets that didn't seem like candidates for cycling before the pandemic.

It is, to be clear, temporary. That’s true of many of the Covid-led interventions that Transport for London is currently making, though those in the know will often quietly admit to hoping they end up being permanent. In this case, however, the agency genuinely seems to mean it: TfL emphasized in its press release that the road space is already being allocated for construction starting late next year and that "TfL will work with local boroughs to develop alternate routes along side streets" when the cycle lane is removed.

At lunchtime on Friday, I decided to try the lane for myself to understand what an unlikely, temporary cycle lane can accomplish. In this case it's clear that the presence of a lane only accomplishes so much. A few key things will still leave riders wanting:

It’s one way only. To be specific, eastbound. I found this out the hard way, after attempting to cycle the Euston Road westbound, under the naive impression that there was now a lane for me in which to do this. Neither I nor the traffic I unexpectedly found myself sharing space with enjoyed the experience. To be fair, London’s cycling commissioner Will Norman had shared this information on Twitter, but cyclists might find themselves inadvertently mixing with multiple lanes of much, much bigger vehicles.

It radically changes in width. At times the westbound route, which is separated from the motor traffic by upright posts, is perhaps a metre and a half wide. At others, such as immediately outside Euston station, it’s shared with buses and is suddenly four or five times that. This is slightly vexing.

It’s extremely short. The publicity for the new lane said it would connect up with other cycle routes on Hampstead Road and Judd Street (where Cycleway 6, the main north-south crosstown route, meets Euston Road). That’s a distance of roughly 925m. It actually runs from Gower Street to Ossulton Street, a distance of barely 670m. Not only does the reduced length mean it doesn’t quite connect to the rest of the network, it also means that the segregated space suddenly stops:

The junction between Euston Road and Ousslston Street, where the segregated lane suddenly, unexpectedly stops. Image: Jonn Elledge.

 

It’s for these reasons, perhaps, that the new lane is not yet seeing many users. Each time I cycled the length of it I saw only a handful of other cyclists (although that did include a man cycling with a child on a seat behind him – not something one would have expected on the Euston Road of the past).


Though I hesitate to mention this because it feeds into the car lobby’s agenda, it was also striking that the westbound traffic – the side of the road which had lost a lane to bikes – was significantly more congested than the eastbound. If the lane is extended, it could, counterintuitively, help, by removing the unexpected pinch points at which three lanes of cars suddenly have to squeeze into two.

There’s a distinctly unfinished air to the project – though, to be fair, it’s early days. The eastbound lane needs to be created from scratch; the westbound extended. At that point, it would hopefully be something TfL would be keen enough to talk about that cyclists start using it in greater numbers – and drivers get the message they should avoid the Euston Road.

The obvious explanation for why TfL is going to all this trouble is that TfL is in charge of the Euston Road, and so can do what it likes there. Building cycle lanes on side nearby roads means working with the boroughs, and that’s inevitably more difficult and time consuming.

But if the long-term plan is to push cyclists via side roads anyway, it’s questionable whether all this disruption is worth it. A segregated cycle lane that stops without warning and leaves you fighting for space with three lanes of buses, lorries, and cabs is a cycle lane that’s of no use at all.

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