Uber trials tech to match passengers who get on well with each other

Uber Pool scientists creating software aimed at minimising risk of in-car bust-ups
Uber hopes to to predict which passengers are at risk of “interpersonal conflict” during Pool trips
AFP/ Getty

A late-night Uber Pool trip might cut your minicab bill but you never can tell who you’ll be travelling with.

Pool journeys are shared by up to three people, cutting 25 per cent off the normal fare, but passengers have complained about sharing with strangers keen to tell their life stories, the “tired and emotional” and troublemakers.

Now, the firm’s data scientists have revealed they are developing software that aims to cut the chances of back seat bust-ups. Uber hopes machine learning, a branch of artificial intelligence, will allow it to predict which passengers are at risk of “interpersonal conflict”.

In a European patent application about software involving “predicting safety incidents”, it says it plans to mine personal data to calculate “safety incident prediction models” — the chance of a row between strangers.

Passengers and drivers would have their Uber profiles scanned to calculate if they are likely to get on and the firm proposes supplementing its data with external offline sources.

The patent says journeys “involve interactions between strangers” and therefore “interpersonal conflicts occasionally occur”.

It adds: “Such incidents, while rare, can have negative consequences, such as property damage and injuries to drivers and passengers.”

The software could also help drivers avoid danger by flashing up safety warnings based on their driving abilities.

The driver’s “quality of driving” would be checked, based on data from their phone, in-car sensors, weather forecasts and crime maps. They would also receive a trustworthiness rating based on psychometric tests, criminal records and complaints about “attitude, dangerous driving, or inappropriate behaviour”.

The new system would then assign a score for the likelihood of a dangerous incident, which the patent says is usually “close to zero”. The application says: “The safety system predicts whether a (driver) is likely to be involved in dangerous driving incidents within the next seven, 14, 30, and 60 days, and whether the provider is likely to be involved in an interpersonal conflict.”

Drivers judged to be behaving riskily would be sent “safety reminder messages”, offered a “mentoring relationship” with another driver, or face a week’s ban.

An Uber spokeswoman: “We are constantly working to build tools to help predict, prevent, and reduce safety risks for our consumers. This patent, like those many companies file, is expansive and covers technologies we continue to research.”

Create a FREE account to continue reading

eros

Registration is a free and easy way to support our journalism.

Join our community where you can: comment on stories; sign up to newsletters; enter competitions and access content on our app.

Your email address

Must be at least 6 characters, include an upper and lower case character and a number

You must be at least 18 years old to create an account

* Required fields

Already have an account? SIGN IN

By clicking Create Account you confirm that your data has been entered correctly and you have read and agree to our Terms of use , Cookie policy and Privacy policy .

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Thank you for registering

Please refresh the page or navigate to another page on the site to be automatically logged in

MORE ABOUT