EX.CO, a leading video technology platform renowned for supporting media giants, has unveiled a sophisticated contextual video content recommendation engine. This innovative engine leverages large language models (LLM) to dynamically suggest the most pertinent videos from a publisher’s archive. This development promises a seamless video integration across websites without the burdensome need for manual curation or bespoke content creation for different articles.
Among the early adopters of this technology is Autovia, a prominent figure in the UK automotive industry with acclaimed brands like Auto Express and Carbuyer. Ciaran Scarry, advertising director at Autovia, emphasized the significance of this upgrade, stating, “Context and relevance are crucial elements of our business as we strive to deliver the best user experience possible. EX.CO’s contextual recommendation engine enhances our UX by allowing us to tailor video recommendations to match the specific content on each page, which is crucial for our in-market audience when they’re researching their next car purchase. This seemingly minor adjustment is a major game changer for us, providing highly-relevant content that captivates our readers and keeps them engaged.
This engine functions by vectorizing text within articles, assessing the similarity with available video content, and optimizing the selection to ensure rapid and accurate video suggestions. For publishers needing a broader range of video content, EX.CO also offers access to a comprehensive content marketplace featuring thousands of videos across various verticals from premium sources.
Tom Pachys, co-founder and CEO of EX.CO, highlighted the advantages over traditional models: “Audiences today will only engage with content that is truly relevant to them; however, it’s challenging for publishers to produce and match such large amounts of video content. After having in-depth conversations with publishers and conducting our own data research, we realized that the old ‘tag/taxonomy’-based approaches were insufficient. By integrating LLM capabilities with ML optimization models, we built a new-generation recommendation engine. We were surprised by the immediate results, which surpassed our previously highly refined models still considered best practice in this field.”
This engine not only enhances user engagement by delivering content ‘at the speed of news‘ but also aims to improve key performance indicators such as revenue, brand loyalty, and subscription rates. Current deployments show an 80% relevancy match rate with quadruple the engagement levels compared to industry norms. Additionally, negative interactions with the video player have decreased by 30-40%.
Looking ahead, EX.CO plans to further refine this technology by incorporating ChatGPT-like functionality, enabling even more precise adjustments based on specific prompts that align with user interests on particular sites or sections.
For small business owners and solopreneurs, this technology represents an opportunity to enhance digital presence and user engagement without extensive resources. As video continues to dominate digital strategy, such tools can be instrumental in staying relevant and competitive in a rapidly evolving market.
