Skip to the lesson

Data and machine learningLesson 1 of 6

Part 1 of 3, 0 done

13 min

Rules or examples? How a filter learns

The game's chat is full of "free skins" scams. Write a rule to stop them, then find out why the filters that really work learn from examples instead.

Ticket 01 · The guess

The filter that learned

Gmail says its protections block more than 99.9%google.com ·2019 of spam, phishing and malware. In 2019 Google added new machine-learning protections on top of the rule-based and machine-learning filters Gmail already had, trained on huge numbers of examples instead of rules typed by people.

About how many extra spam messages a day did it start blocking?

250 million messages a day
0500 million
Words to know

Spot something wrong?

Tell us what looks off. No name or email needed.

What kind of problem?

0 / 1000

We'll also send this page, the lesson, ticket 1, so we can find it. Nothing else. Privacy

·
Sources and every number (2)

Sources

  • Ridding Gmail of 100 million more spam messages with TensorFlow (Neil Kumaran, February 6, 2019) · Google Workspace blog, 2019
  • A Plan for Spam (August 2002) · Paul Graham, 2002

Every number

  • 99.9%google.com ·2019 · Share of spam, phishing and malware Gmail says its protections block (Google, February 2019); "more than".
  • 100 million messages a daygoogle.com ·2019 · Extra spam Gmail blocked each day after adding new machine-learning protections built with TensorFlow, about, February 2019.
  • 200 messagesexample (example number: Simplified example: messages the moderators labeled.) · Simplified example: messages the moderators labeled.
  • 40 messagesexample (example number: Simplified example: labeled messages with a link from an account less than a week old.) · Simplified example: labeled messages with a link from an account less than a week old.
  • 34 messagesexample (example number: Simplified example: of those, the ones labeled scam.) · Simplified example: of those, the ones labeled scam.
  • 85%example (example number: Worked out: 34 messages ÷ 40 messages.) · Worked out: 34 messages ÷ 40 messages.
  • 160 messagesexample (example number: Worked out: 200 messages − 40 messages.) · Worked out: 200 messages − 40 messages.
  • 4 messagesexample (example number: Simplified example: scams among the other labeled messages.) · Simplified example: scams among the other labeled messages.
  • 2.5%example (example number: Worked out: 4 messages ÷ 160 messages.) · Worked out: 4 messages ÷ 160 messages.
  • 17%example (example number: Worked out, the wrong way: 34 messages ÷ 200 messages.) · Worked out, the wrong way: 34 messages ÷ 200 messages.
  1. Lessons›
  2. The school›
  3. Data and machine learning
  • ·Next: Predict tomorrow's iced coffees