Online reviews can predict the failure of 7 out of 10 businesses, study claims

Researchers have developed a tool that uses customer ratings to analyse restaurants’ likelihood of success.

Can artificial intelligence predict a restaurant's likelihood of failure?

By analysing online customer ratings, researchers from Rotterdam School of Management, Erasmus University (RSM) say that they have developed a model that can do so, 70% of the time.  

The trio of Dr. Markus Weinmann, Christof Naumzik and Prof. Stefan Feueriegel used almost 65,000 customer ratings from more than 900 restaurants as the input for their data analysis, and developed the AI model to estimate the most likely “state” that a restaurant is in. 

They found three states: restaurants that get bad ratings but are still in business, restaurants that get good ratings and are still in business, and restaurants that have very dispersed ratings (ranging from very positive to very negative) and are still in business.

Restaurants under the third state, they claim, are most at risk, and have a likelihood of failure which is twice as high as restaurants in the other two states, claiming their AI model can “detect these business failures, even months ahead.”

“The restaurant market is very volatile and dynamic. Even minor changes – such as updating a menu or a change of personnel ‒ can make customers switch their loyalty. The success, or even the survival, of service businesses depends on their ability to satisfy their customers. Yet, businesses are often too late to recognise slumping customer satisfaction and suffer the ultimate failure. So an early warning system for restaurants would help them to adjust their service offerings in time,” Weinmann said in a media release.