Jun 14, 2017

Uber says it has improved its AI to forecast driver demand

Seth Wenig/AP

Uber is in the prediction business, but it wants to get better. So the company's artificial intelligence team has proposed a new algorithm that it says improves its forecasting of demand in extreme situations like bad weather and major holidays.

Uber researchers are applying a machine-learning architecture called "long short-term memory" (LSTM) to predict demand for drivers during "holidays, concerts, inclement weather, and sporting events." In a new blog post, they said that this new approach improved the accuracy of their existing forecasting algorithm between 2% and 18%.

Why it matters: Better AI forecasting models could impact fields as diverse as medicine and earthquake prediction. The latest craze among hedge funders is using LSTM architecture to predict asset price changes.

How it works: Traditional statistical modeling requires humans to decide the relevance of historical data to the given forecast. In the LSTM architecture, a predictive algorithm improves itself by finding data relationships otherwise unrecognized by humans. In Uber's case, these data are the number of completed rides, app views, current riders, outside temperature, and wind speed.

Go deeper

Mass shooting in Milwaukee: What we know so far

Milwaukee Mayor Tom Barrett in 2012. Photo: John Gress/Corbis via Getty Images

Six people died in a shooting at the Milwaukee Molson Coors brewery complex on Wednesday, including the shooter, Mayor Tom Barrett told reporters at an evening press conference with local police.

What's happening: Police said "there is no active threat" just before 6 pm ET, but noted the scene remains active. Police chief Alfonso Morales told reporters that officers have "more than 20 buildings we have to secure" at the complex and they do not currently have all employees accounted for, as more than 1,000 were at the complex during the shooting.

Go deeperArrowUpdated 24 mins ago - Politics & Policy

Live updates: CDC confirms possible community spread of coronavirus

Data: The Center for Systems Science and Engineering at Johns Hopkins, the CDC, and China's Health Ministry. Note: China numbers are for the mainland only and U.S. numbers include repatriated citizens.

U.S. clinicians have found the novel coronavirus in a person who did not recently return from a foreign country nor have contact with a confirmed case, the CDC said Tuesday.

The big picture: COVID-19 has killed more than 2,700 people and infected over 81,000 others. By Wednesday morning, South Korea had the most cases outside China, with 1,261 infections. Europe's biggest outbreak is in Italy, where 374 cases have been confirmed.

Go deeperArrowUpdated 40 mins ago - Health

Trump assigns Pence to lead U.S. coronavirus response


President Trump announced at a press briefing Wednesday evening that he'll be putting Vice President Mike Pence in charge of leading the administration's response to the coronavirus.

The big picture: In the wake of a market sell-off and warnings from health officials that there's a real threat of the coronavirus spreading in the U.S., Trump sought to reassure the nation and Wall Street that the U.S. is "ready" for whatever comes next.

Go deeperArrowUpdated 2 hours ago - Politics & Policy