Content recommendation

Data analytics, machine learning and optimization.


A national media content and distribution company wanted personalized content recommendations integrated into existing editorial tools and workflows.


  • Personalized content recommendations in applications for media consumption.

  • Development of content recommendation based on customer profiles, viewing history and content metadata.

  • Deployment of robust real-time recommendations for all customers through an API, served to multiple frontend client applications.

Sonat Service

  • Extending existing data collection, as well as cleanup, processing and analytics.

  • Trained, deployed and evaluated models for performant real-time recommendations.

  • Ongoing extension of the recommendation system to all content delivered to the customers, as well as extension of the types of content recommendation.

The Results

  • Successful deployment of a content recommendation system.
  • Improved click through rate by 50 % compared to editorially selected content recommendations.
  • Architecture and development of an API to client facing applications, and a scalable, high-availability microservice architecture running on Kubernetes.

Content recommendation


Improved click rate

Content recommendation algorithms give users
personalized recommendations based on previous activity.

It’s famously used by companies such as Netflix and Amazon,
which respectively recommend media content and retail items.

While the prototypical examples are large companies,
there is no reason why smaller companies can not benefit from
delivering personalized content recommendation too.

Sonat AI

Data analytics, machine learning and optimization.


Kjell Værøy Ljøstad

CEO Oslo
+47 952 67 129

Sonat Consulting Oslo AS
Karl Johansgt. 25
0159 Oslo


Jonny Klemetsen

CEO Bergen
+47 294 56 245

Sonat Consulting Bergen AS


C. Sundts gate 17-19

5008 Bergen


Sonat Consulting Bergen AS

Postboks 234 Sentrum

5804 Bergen