Scribd
Upload
6 views

Netflix

Product discovery

Uploaded by

Chinmay Biliya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
6 views

Netflix

Product discovery

Uploaded by

Chinmay Biliya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 9

Product Discovery Process

Netflix was the first OTT platform to build a


recommendation engine in the early 2000s.

Let’s take a look at the product discovery process of the


Netflix recommendation engine.
Key user problem solved

Users were overwhelmed by the vast library of content


and needed an easy way to discover movies and shows
that they would enjoy
User research

They conducted extensive user interviews and surveys to


understand viewing preferences, habits and pain points
related to content discovery
Testing

They conducted various A/B tests on their


recommendation system and user interface some of
which are mentioned below:
Testing

Recommendation algorithms: They tested different algorithms,


including how content is ranked/ displayed to see which one would yield
better user engagement

Thumbnails: They tested and continue to test different thumbnails for the
same content to understand which ones get more clicks

Personalization: They test how personalised their recommendations are


based on user behaviour and preferences
Testing

Row organisation: They tested various ways in which rows are organised
to see and the order in which they appear to see which way got more
engagement

Notifications and recommendations: They tested how these


recommendations were made recommending content based on user
behaviour to see which format leads to maximum engagement

It is important to note that this was not an isolated exercise, but a


continuous process that they engage in, even over a decade after the
system was launched
Testing

Notifications and recommendations: They tested how these


recommendations were made (through in-app and push
notifications) recommending content based on user behaviour
to see which format leads to maximum engagement

It is important to note that this was not an isolated exercise,


but a continuous process that they engage in, even over a
decade after the system was launched
Competitor response

Competitors like Amazon soon followed and developed their own


recommendation algorithms, however, Netflix’s pioneering move
remains a case study for the ages

You might also like