“We didn't have a state-of-the-art machine learning model. That's not what existed back then. But we had rules in place and we did regression learning around, you know, kind of deciding what to serve.”

David Senra · High School Dropout to Multi-Billionaire: The Relentless Drive of Rafael Vivas

Play from 17:36
17:36

Audio streams from the publisher’s own feed. Verbatim does not host or copy it.

What was described

implemented rule-based regression learning to decide which ads to serve instead of using a state-of-the-art ML model

Said nearby on the same subject

“We had this model, which was 100% pay for 80% time for 100% output. And any company who decided to work with us and experiment worked in accordance with that model.”
♫
Said on The Business
Why it worked 100% pay, 80% time, 100% output Share this moment
“The $60 million paragraph that was added to advertisements that I ran that added $60 million in sales”
♫
Said on Entrepreneurs on Fire
Why it worked $60 million in sales Share this moment
“We use the kind of, um, machine learning approach, AI approach called end-to-end models, which are more powerful, but innately more complicated to get working”
♫
Said on Profiles in Risk
Why it worked Share this moment
“We decided to implement the free shipping at $100. I think that was probably the middle of the summer, maybe the beginning of the summer.”
DP
Damian Primis
Unit Economics ·
Pricing $100 minimum order for free shipping Share this moment

Moments like this, every Monday

The strongest new moments on your topics, in the speakers' own words. Your first brief is free, then USD {{ TIERS.starter.price }} a month for three topics.

No card to start. No password. Cancel any time.

Track a competitor?

Pro watches up to 25 names or phrases and emails you the morning after they are said.

See Pro, $29 a month

Verbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.