Videogram implements Machine Learning techniques across its state-of-the-art models of video content and user behavior. Pixel by pixel, click by click, big data is collected and analysed to improve model accuracy and deliver the most engaging user experience. From proprietary, user-adjusting video presentation format, to accurate voice, object and scene search, all Videogram models constantly morph and evolve according to user preferences, effectively removing consumption bottlenecks across all online video real estate (Web, Smart TV, Mobile).