RTL Interactive
TV

Recommend the right movies

RTL wanted to build up more machine learning competencies in-house and operate core technologies themselves. We developed an end-to-end solution for the team that implements a hybrid recommendation algorithm.

As part of our four-screen strategy, we want to offer every user the best user experience with our content on all end devices. Intelligent data-driven processes are a key element of this strategy. It was important to us that our partner already has a track record in a similar area and has already successfully implemented similar projects. Data Revenue was a great fit. I enjoy working with smaller companies because we can implement our topics very quickly and in a pragmatic way with them

Volker Stümpflen

,

Head of Data Strategy and Operations

Tools we used

AWS
-
One stop for compute infrastructure.
Dask
-
Leaves Spark in the dust.
Docker
-
Portable, flexible and simple deployments.
Kubernetes
-
Faster, more efficient and agile infrastructure.
Luigi
-
For managing all tasks in an execution graph – like Airflow.
Pandas
-
Great for exploration and feature engineering.
Python
-
Our main development language.
LightFM
-
Hybrid recommender tool.