Our SaaS offering is the perfect match for video discoveries, Video on Demand Providers, IPTV and OTT Platforms to reinvent how viewers discover, watch and share video content across devices and platforms.
Software as a Service
Video and TV content is moving to the cloud, allowing fans to access from desktop computers, smartphones, connected TVs, and tablets whenever they prefer. We are approaching the inevitable point at which this becomes mainstream TV watching behaviour. All viewers will enjoy tremendous advantages. However, messy metadata, content fragmentation and diverse customer demands present huge challenges to service providers.
The Tweek Taste Profiler™, Context and Recommendation Engine provide those services with a deep understanding of customers and their favourite content to deliver a world class end-to-end consumer experiences, increasing return rates and usage times.
We at Tweek fight the dilemma of choice: Today's on-demand services offer viewers millions of videos, movies, TV shows, causing a need for technology capable of finding the right content to watch.
The Tweek Engine knows consumers and video content. It connects and enriches them through structured metadata and semantics. Based on a constantly growing number of data points and end user solutions running on top of our API, we are powering the ecosystem to re-invent how viewers discover, watch and share video content.
The Taste Profiler™ is our mining engine for the social web. It connects your content ecosystem with realtime user data from around the web to increase service personalization and stickiness. By applying the Taste Profiler™, you as a developer can maintain an in-depth understanding of your users' activity and video preferences.
The Taste Profiler™ parses already existing user data that can be related to movie, TV show or live TV content from sides connected to the social web data infrastructure.
As a result, it enables personalisation from day one and puts an end to cold start problems within your service. This makes the 1st time usage more personal and decreases churn rates, significantly.
Also, the Taste Profiler™ keeps the user profile in constant sync with related web activity which increases service stickiness and customer satisfaction in the mid to long run.
The Context Engine is a matching technology harvesting contextual information around video content from sources such as wikipedia, imdb, official Facebook Pages, hashtags, celebrity tweets and latest gossip to ensure currentness of content.
The discovery of content as we have known it for years is driven via metadata. Genre information and actors are standard ways to browse and filter through content, quickly. Stills and trailers make you decide. The social web carries an increasing number of data points to enrich content: The opinion of friends driven via Taste Profiler™ is enhanced through their tweets, celebrity tweets, latest gossip around the show or the actor.
The Context Engine provides you with the unique chance to keep your service relevant and fresh to reach the 18-34 year old target group. Utilize our dynamic data feeds and connect your users to the online video conversation around shows and artists.
Delivering the right content for each user is more important than ever before as options for consumers rise and noise is constantly present. The average users' attention span has never been this challenging for service providers.
We provide you with two core tools to deliver great recommendations: Clean data plus latest hybrid recommender technology:
a. Seeding with a vast amount of metadata makes it less challenging to ensure compatibility among viewers (user-to-user approach). Seeding with a structured pool of data makes it easier to compare content items (item-to-item).
b. Integrating a hybrid approach of combining the above collaborative filtering with semantic based recommendation makes our Recommender a unique service enhancement for your offering.
An outstanding discovery experience is ensured by combining the Recommender with the unique Taste Profiler™ as this fully utilizes the power of the social web to fuel the next generation of semantic content recommendation based on personal likes, personal profile information, friends' recommendations, watching behavior, and detailed profile information such as movie and sports team preferences.