Sign In

Communications of the ACM

ACM TechNews

Social Media Data Used to Predict Retail Failure


A retail districte in Seoul, Korea.

An international team led by researchers has developed a model that can predict whether a new retail business will fail within six months.

Credit: Kim Ji-hyun/The Korea Herald

An international team led by researchers at the University of Cambridge in the U.K. has developed a model based on social media and transport data that can predict with 80% accuracy whether a new business will fail within six months.

The researchers used more than 74 million check-ins from the location-based social network Foursquare from Chicago, Helsinki, Jakarta, London, Los Angeles, New York, Paris, San Francisco, Singapore, and Tokyo, and data from 181 million taxi trips in New York and Singapore. They used this data to classify venues according to the properties of the neighborhoods in which they are located, the visit patterns at different times of day, and whether a neighborhood attracted visitors from other neighborhoods.

The data shows venues in diverse neighborhoods with multiple types of businesses tend to survive longer.

The researchers will present their findings at this week's ACM Conference on Pervasive and Ubiquitous Computing (Ubicomp) in Singapore.

From University of Cambridge
View Full Article

 

Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA


 

No entries found