Youyang Gu – Covid's Data Superstar
Bloomberg Businessweek|March 01, 2021
It was global public-health institutions vs. a guy living with his parents in California
By Ashlee Vance

Spring 2020 brought with it the arrival of the celebrity statistical model. As people tried to gauge how big a deal the novel coronavirus might be, they were pointed again and again to two forecasting systems: one built by Imperial College London, the other by the Institute for Health Metrics and Evaluation, or IHME, based in Seattle.

But the models yielded wildly divergent predictions. Imperial warned that the U.S. might see as many as 2 million Covid-19 deaths by the summer, while the IHME forecast just 60,000 deaths. Neither, it turned out, was very close. The U.S. ultimately reached about 160,000 deaths by the start of August.

The huge discrepancy in the forecasting figures that spring caught the attention of a young data scientist named Youyang Gu. The 26-year-old had a master’s degree in electrical engineering and computer science from the Massachusetts Institute of Technology and another degree in mathematics, but he had no formal training in a health-related area such as biology or epidemiology. Still, he thought his background dealing with data models could prove useful during the pandemic.

In mid-April, while he was living with his parents in Santa Clara, Calif., Gu spent a week building his own Covid death predictor and a website to display the morbid information. Before long, his model started producing more accurate results than those cooked up by institutions with hundreds of millions of dollars in funding and decades of experience.

“His model was the only one that seemed sane,” says Jeremy Howard, a data expert and research scientist at the University of San Francisco. “Peoples’ lives were depending on these things, and Youyang was the one person actually looking at the data and doing it properly.”

The forecasting model that Gu built was, in some ways, simple. Covid tests, hospitalizations, and other metrics were being reported inconsistently, so he used the most reliable data: daily death counts. “Having that as the only input helped filter the signal from the noise,” Gu says.

Continue reading your story on the app

Continue reading your story in the magazine

MORE STORIES FROM BLOOMBERG BUSINESSWEEKView All

The Food Fight in Fake Meat

Beyond Meat was an early leader. But rival Impossible Foods and others want to eat its lunch

6 mins read
Bloomberg Businessweek
April 19, 2021

The U.K. Wants to Clean Up Space

The amount of debris in orbit is an increasing danger—and a potential market opportunity

4 mins read
Bloomberg Businessweek
April 19, 2021

Peak Pallet

Prices for a warehouse staple are at a record, buoyed by the boom in e-commerce

4 mins read
Bloomberg Businessweek
April 19, 2021

THE MAN WHO KEEPS THE FAR RIGHT ONLINE

While Amazon and its peers have stopped supporting certain prominent White supremacists and conspiracy theorists, Nick Lim has stepped in

10+ mins read
Bloomberg Businessweek
April 19, 2021

Stopping the Race to the Bottom on Taxes

The U.S. is energizing a global effort to put a floor under corporate tax rates

8 mins read
Bloomberg Businessweek
April 19, 2021

The Guggenheims Of NFTs

Perhaps you’ve heard of nonfungible tokens? These collectors already have millions of dollars’ worth

10 mins read
Bloomberg Businessweek
April 19, 2021

Reincarnation And Realpolitik

China, India, and the U.S. are vying to influence the selection of the next Dalai Lama

5 mins read
Bloomberg Businessweek
April 19, 2021

WAITING FOR ELON

It’s not easy to compete with Miami and Austin for high-tech jobs. But Adelanto, Calif., which boasts a light regulatory environment, an enthusiastic city manager, and plenty of dirt, is giving it a shot

10+ mins read
Bloomberg Businessweek
April 19, 2021

LAW & CRYPTO

Arthur Hayes faces U.S. prosecution over how he ran his overseas Bitcoin exchange

5 mins read
Bloomberg Businessweek
April 19, 2021

In Hot Pursuit

Chris Urmson’s company, Aurora, has merged with Uber’s self-driving unit to take on Waymo

7 mins read
Bloomberg Businessweek
April 19, 2021