T E C H N O L O G Y
22
16
Edited by
Anne VanderMey
and David Rocks● It was global public-health
institutions vs. a guy living with
his parents in CaliforniaCovid’s Data Superstar
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 predic-
tions. 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 sci-
entist named Youyang Gu. The 26-year-old had a
master’s degree in electrical engineering and com-
puter science from the Massachusetts Institute
of Technology and another degree in mathemat-
ics, but he had no formal training in a health-
related area such as biology or epidemiology. Still,
he thought his background dealing with data mod-
els 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 sci-
entist 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 inconsis-
tently, 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.The novel, sophisticated twist of Gu’s model
came from his use of machine learning algo-
rithms. After MIT, Gu spent a couple years work-
ing in the financial industry writing algorithms for
high- frequency trading systems in which his fore-
casts had to be accurate if he wanted to keep his
job. When it came to Covid, Gu kept comparing his
predictions to the eventual reported death totals
and constantly fine-tuned his software. The work
required the same hours as a full-time job, but Gu
volunteered his time and lived off his savings.
While certainly not perfect, Gu’s model per-
formed well from the outset. In late April he pre-
dicted the U.S. would see 80,000 deaths by May 9.
The actual death toll was 79,926. A similar late-
April forecast from the IHME predicted that the
U.S. would not surpass 80,000 deaths through all
of 2020. Gu also predicted a total of 90,000 deaths
by May 18 and 100,000 by May 27, and he once
again got the numbers right. Where the IHME
expected the virus to largely fade away as a
result of social distancing, Gu predicted a second
wave of infections and deaths as states reopened
from lockdowns.
The IHME faced some criticism in March and
April, when its numbers didn’t match reality. Still,
the prestigious center, based at the University of
Washington and bolstered by more than $500 mil-
lion in funding from the Bill & Melinda Gates
Foundation, was cited on an almost daily basis in
government briefings. In early April, U.S. infec-
tious disease chief Anthony Fauci said Covid’s total
death toll “looks more like 60,000 than the 100,
to 200,000” once expected—a prediction that
reflected IHME forecasts. And on April 19, the same
day Gu cautioned about a second wave, President
Donald Trump pointed to the IHME’s data as a sign
the pandemic would soon be over.
The organization’s officials also actively pro-
moted their numbers. “You had the IHME on all
these news shows trying to tell people that deaths
would go to zero by July,” Gu says. “Anyone with
common sense could see we would be at 1,000 to
1,500 daily deaths for a while. I thought it was very
disingenuous for them to do that.”
Christopher Murray, the director of the IHME,
says that once the organization got a better han-
dle on the virus after April, its forecasts improved. PHOTOGRAPH BY JUSTIN WEE FOR BLOOMBERG BUSINESSWEEKBloomberg Businessweek March 1, 2021