Predicting Viewer Preferences: Transforming Media Engagement with Real-Time Recommendation Models
Introduction
Algorithms to improve the user experience
Client
Media & Entertainment
Client since
Services
Solutions
Technologies
The problem
Algorithms to improve the user experience
Our client, a public company providing a broad range of media services, wants to improve the user experience of their online platform. In order to do so, they request Datashift to implement a recommendation engine on their website using all available historical data and content metadata to predict which content will be of interest to an individual user.
The algorithm used and recommendations made to the user, should be real time and immediately available for the viewer. In order to achieve this, an intense and close collaboration between business, IT and data (data scientists and data engineers) was needed.
How we solved it
Combining the power of data science with the force of data engineering
The goal was to set up a model that can make recommendations based on historic usage & content metadata. After A/B testing a couple of algorithms the choice was made to implement a hybrid model that retrains itself on a continuous basis as new usage data comes in. A lot of focus was put on making the model as efficient as possible in order to run very close to real-time.
As the output of the algorithm needs to be available in real-time, a pipeline was set up to write the recommendations to a DynamoDB database. An API gateway was then set up to be able to query this data quickly. In parallel a system of metrics was set up in order to be able to measure the efficiency of the recommendation model & the speed of the API call.
Datashift took the lead in model development and added additional architecture and engineering support where necessary. The collaboration with internal teams was key to ensure the predicting model generates results in an optimal environment. Development was done in an agile way in order to work in short, well-defined tasks and get quick user feedback.
Combining the power of data science with the force of data engineering
The goal was to set up a model that can make recommendations based on historic usage & content metadata. After A/B testing a couple of algorithms the choice was made to implement a hybrid model that retrains itself on a continuous basis as new usage data comes in. A lot of focus was put on making the model as efficient as possible in order to run very close to real-time.
As the output of the algorithm needs to be available in real-time, a pipeline was set up to write the recommendations to a DynamoDB database. An API gateway was then set up to be able to query this data quickly. In parallel a system of metrics was set up in order to be able to measure the efficiency of the recommendation model & the speed of the API call.
Datashift took the lead in model development and added additional architecture and engineering support where necessary. The collaboration with internal teams was key to ensure the predicting model generates results in an optimal environment. Development was done in an agile way in order to work in short, well-defined tasks and get quick user feedback.
The results
Automated personalization for every individual user
Due to the close collaboration between Datashift and the in-house engineers, we achieved excellent results. Traffic is going up as well as interactions with users, giving us more data to further improve user experience. In the future we expect users to consume more content and stay longer on the platform. Bingewatch alert! :)
After this initial mission, the client asked us to create a roadmap to further use data and AI to improve user experience (e.g. cross brand recommendations).
Key Learnings
More case studies
We deliver impact where it matters most.
Unlocking Viewer Insights with a Scalable Data Platform
Streamz is the Flemish video-on-demand platform offering local and international series and films through a subscription-based model. Streamz focuses on delivering high-quality content tailored to local audiences, supported by a strategic partnership with Paramount.
