ClassroomThe classroom
Back to the lesson libraryMECHANISM · 11 MIN
M33.8 CONNECT THE MECHANISM

Apply the same lifecycle questions to different products

Netflix paid a million dollars for a better recommender and never shipped it. Four real deployments show which step of this module decided each one's fate.

LESSON OVERVIEW11 min lesson

Lesson overview

Netflix paid a million dollars for a better recommender and never shipped it. Four real deployments show which step of this module decided each one's fate.

What you’ll explore

  • Compare real AI deployments in recommendation, forecasting, accessibility, and decision support by what was predicted, how it was judged offline, what happened in use, and which lifecycle step made the difference, then apply the same questions to a new product.
GO TO THE SOURCE

Original explanations, connected to the research.

Netflix Recommendations, Beyond the 5 Stars, Part 1 (Netflix Technology Blog, 2012)The Netflix Recommender System: Algorithms, Business Value, and Innovation (Gomez-Uribe & Hunt, ACM TMIS, 2015)The Parable of Google Flu: Traps in Big Data Analysis (Lazer, Kennedy, King & Vespignani, Science, 2014)External Validation of a Widely Implemented Proprietary Sepsis Prediction Model in Hospitalized Patients (Wong et al., JAMA Internal Medicine, 2021)Racial Disparities in Automated Speech Recognition (Koenecke et al., PNAS, 2020)
Suggest a correction

A precise note can make an explanation better.

Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.

The file includes this note, the scene title, and lesson metadata. Your saved progress and quiz responses are excluded. Download before leaving or reloading to keep your note.