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.

 
 
 
 

CityMetric is now City Monitor! Come see us at our new home

City Monitor is now live in beta at citymonitor.ai.

CityMetric is now City Monitor, a name that reflects both a ramping up of our ambitions as well as our membership in a network of like-minded publications from New Statesman Media Group. Our new site is now live in beta, so please visit us there going forward. Here’s what CityMetric readers should know about this exciting transition.  

Regular CityMetric readers may have already noticed a few changes around here since the spring. CityMetric’s beloved founding editor, Jonn Elledge, has moved on to some new adventures, and a new team has formed to take the site into the future. It’s led by yours truly – I’m Sommer Mathis, the editor-in-chief of City Monitor. Hello!

My background includes having served as the founding editor of CityLab, editor-in-chief of Atlas Obscura, and editor-in-chief of DCist, a local news publication in the District of Columbia. I’ve been reporting on and writing about cities in one way or another for the past 15 years. To me, there is no more important story in the world right now than how cities are changing and adapting to an increasingly challenging global landscape. The majority of the world’s population lives in cities, and if we’re ever going to be able to tackle the most pressing issues currently facing our planet – the climate emergency, rising inequality, the Covid-19 pandemic ­­­– cities are going to have to lead the way.

That’s why City Monitor is now a global publication dedicated to the future of cities everywhere – not just in the UK (nor for that matter just in the US, where I live). Our mission is to help our readers, many of whom are in leadership positions around the globe, navigate how cities are changing and discover what’s next in the world of urban policy. We’ll do that through original reporting, expert opinion and most crucially, a data-driven approach that emphasises evidence and rigorous analysis. We want to arm local decision-makers and those they work in concert with – whether that’s elected officials, bureaucratic leaders, policy advocates, neighbourhood activists, academics and researchers, entrepreneurs, or plain-old engaged citizens – with real insights and potential answers to tough problems. Subjects we cover include transportation, infrastructure, housing, urban design, public safety, the environment, the economy, and much more.

The City Monitor team is made up of some of the most experienced urban policy journalists in the world. Our managing editor is Adam Sneed, also a CityLab alum where he served as a senior associate editor. Before that he was a technology reporter at Politico. Allison Arieff is City Monitor’s senior editor. She was previously editorial director of the urban planning and policy think tank SPUR, as well as a contributing columnist for The New York Times. Staff writer Jake Blumgart most recently covered development, housing and politics for WHYY, the local public radio station in Philadelphia. And our data reporter is Alexandra Kanik, whose previous roles include data reporting for Louisville Public Media in Kentucky and PublicSource in Pittsburgh, Pennsylvania.

Our team will continue to grow in the coming weeks, and we’ll also be collaborating closely with our editorial colleagues across New Statesman Media Group. In fact, we’re launching a whole network of new publications, covering topics such as the clean energy transition, foreign direct investment, technology, banks and more. Many of these sectors will frequently overlap with our cities coverage, and a key part of our plan is make the most of the expertise that all of these newsrooms combined will bring to bear on our journalism.

Please visit citymonitor.ai going forward, where you can also sign up for our free email newsletter.


As for CityMetric, some of its archives have already been moved over to the new website, and the rest will follow not long after. If you’re looking for a favourite piece from CityMetric’s past, for a time you’ll still be able to find it here, but before long the whole archive will move over to City Monitor.

On behalf of the City Monitor team, I’m thrilled to invite you to come along for the ride at our new digs. You can follow City Monitor on LinkedIn and on Twitter. If you’re interested in learning more about the potential for a commercial partnership with City Monitor, please get in touch with our director of partnerships, Joe Maughan.

I want to thank and congratulate Jonn Elledge on a brilliant run. Everything we do from here on out will be building on the legacy of his work, and the community that he built here at CityMetric. Cheers, Jonn!

To our readers, on behalf of the City Monitor team, thank you from all of us for being such loyal CityMetric fans. We couldn’t have done any of this without you.

Sommer Mathis is editor-in-chief of City Monitor.