Uploaded April 2022 | Updated September 2026, 2 weeks ago
Youyang Gu is the creator of http://covid19-projections.com. In 2020, while most Covid prediction model failed, without any experience in medicine he created a forecasting model that outperforms almost all medical experts. Yann LeCun, Facebook's chief AI scientist and professor stated that Gu's model "is the most accurate to predict deaths from COVID-19", surpassing the accuracy of the well-funded Institute for Health Metrics and Evaluation COVID model. It was cited by the Centers for Disease Control (CDC) in its estimates for U.S. recovery. (See timestamps below)
Currently, he is a member of the Technical Advisory Group at the World Health Organization. Working on laying the groundwork for a comprehensive, global study to document and analyze differences in levels of mortality attributable to COVID-19 between and within countries.
Today we talked about how he built the model, lessons he learned, his advice for data scientists and what his working on today. If you like the show subscribe to the channel and give us a 5-star review. Subscribe to Daliana's newsletter on dalianaliu.com for more on data science.
Daliana's LinkedIn: linkedin.com/in/dalianaliu
Daliana's Twitter: twitter.com/DalianaLiu
Youyang's blog: youyanggu.com
Youyang's Twitter: twitter.com/youyanggu
Timestamps:
00:00:00 How he built the best Covid forecasting model
00:01:53 How he got into data science
00:03:58 How he started the Covid forecasting model
00:05:47 How he handled data quality issues
00:10:28 How he created the first version of the model
00:36:19 How he improved the model
00:46:43 How Twitter helped him get feedback for his model
00:50:15 Why he doesn't use Twitter as much as before
00:51:26 How he handled criticism
01:00:53 How he remained confidence about his model under pressure
01:10:35 How the absence of medical experience became an advantage
01:13:42 How to avoid groupthink and biases
01:15:14 Common mistakes data scientists make
01:16:54 The best way to test your model
01:18:51 How to select data and features
01:22:10 How he learned the domain knowledge about public health
01:30:19 How to find wisdom through crowdsourcing
01:33:07 Books and blogs that influenced him
01:37:04 His work with WHO
01:41:15 His current day-to-day for this project
01:44:37 Data science best practices and mistakes to avoid
01:47:19 How to select features
01:49:56 His advice for data scientist
01:51:16 The next steps of his career
01:53:42 A side project he is interested in
01:56:22 His life outside of data science
02:01:12 Where people can find him online
Youyang Gu is the creator of http://covid19-projections.com. In 2020, while most Covid prediction model failed, without any experience in medicine he created a forecasting model that outperforms almost all medical experts. Yann LeCun, Facebook's chief AI scientist and professor stated that Gu's model "is the most accurate to predict deaths from COVID-19", surpassing the accuracy of the well-funded Institute for Health Metrics and Evaluation COVID model. It was cited by the Centers for Disease Control (CDC) in its estimates for U.S. recovery. (See timestamps below)
Currently, he is a member of the Technical Advisory Group at the World Health Organization. Working on laying the groundwork for a comprehensive, global study to document and analyze differences in levels of mortality attributable to COVID-19 between and within countries.
Today we talked about how he built the model, lessons he learned, his advice for data scientists and what his working on today. If you like the show subscribe to the channel and give us a 5-star review. Subscribe to Daliana's newsletter on dalianaliu.com for more on data science.
Daliana's LinkedIn: linkedin.com/in/dalianaliu
Daliana's Twitter: twitter.com/DalianaLiu
Youyang's blog: youyanggu.com
Youyang's Twitter: twitter.com/youyanggu
Timestamps:
00:00:00 How he built the best Covid forecasting model
00:01:53 How he got into data science
00:03:58 How he started the Covid forecasting model
00:05:47 How he handled data quality issues
00:10:28 How he created the first version of the model
00:36:19 How he improved the model
00:46:43 How Twitter helped him get feedback for his model
00:50:15 Why he doesn't use Twitter as much as before
00:51:26 How he handled criticism
01:00:53 How he remained confidence about his model under pressure
01:10:35 How the absence of medical experience became an advantage
01:13:42 How to avoid groupthink and biases
01:15:14 Common mistakes data scientists make
01:16:54 The best way to test your model
01:18:51 How to select data and features
01:22:10 How he learned the domain knowledge about public health
01:30:19 How to find wisdom through crowdsourcing
01:33:07 Books and blogs that influenced him
01:37:04 His work with WHO
01:41:15 His current day-to-day for this project
01:44:37 Data science best practices and mistakes to avoid
01:47:19 How to select features
01:49:56 His advice for data scientist
01:51:16 The next steps of his career
01:53:42 A side project he is interested in
01:56:22 His life outside of data science
02:01:12 Where people can find him online
