Social feed and video recommender for Frever
Social feed and video recommender for Frever
Frever’s unique video-creation and social content sharing app enables their users’ creativity. Users create personalized avatars and express themselves through music videos, stories, and vlogs.
Background
In Frever’s app, users create and share short animated videos, by creating avatars and building scenes, adding voice and music. The videos are shared and content is discovered through a TikTok-like feed. Users can share, comment, and like videos of fellow creators, as well as produce remixes. In order to offer the best possible user experience, a relevant and personalized feed, that captures users’ engagement and stimulates creativity is of central interest.
Solution
Engineers at Frever and Modulai teamed up in close collaboration to create an end-to-end machine-learning-based feed recommender system. A multi-model system architecture was developed and populates the feeds of every user. Information about the content of the video as well as indicators of the users’ preferences is taken into account to ensure the best possible experience and relevance.
Tools/Tech
A fully cloud-based solution was developed for the training, validation, and deployment of content-based and collaborative filtering models. Coding was mainly done in Python as dockerized microservices. A set of internal APIs passes input data and recommendations between the producing and consuming systems.
Wanna discuss our AI solutions for Social networks?
Related cases
Recommendation system for Skincity
Providing accurate skin product recommendations online is difficult. We built a system that combines the knowledge of the skin therapists with product- and customer behavior data to increase product recommendation accuracy with the aim of driving higher conversion rates and customer satisfaction.
The client is an online skincare clinic that offers a finely-tuned selection of professional skin care products and make-up. Central to their operation are the customized product recommendations customers receive from their experienced skincare therapists.
Real-time and In-session: state-of-the-art recommender system for Ahlsell
The Modulai team worked together with Ahlsell’s Applied AI team to develop a real-time session-based recommender system. The system weighs a customer’s intent in a given session on their website or smartphone app to provide contextually relevant recommendations.
In a case like this, careful balancing of model complexity and predictive performance is key to best meet Ahlsell’s needs. Higher predictive performance means customers getting recommendations better suited to their needs, indirectly increasing Ahlsell’s revenue. However, real-time, low-latency inference in the cloud is not free, and customer experience is negatively impacted by slow(er) load times.
