Timely, relevant business news is essential for professionals who develop and manage commercial relationships between organizations. Business-to-business (B2B) sales executives, account managers, and advisors rely on up to the minute news to provide crucial context for decision-making and may reveal opportunities for for new or expanded commercial engagements. However, keeping up with the immense volume, complexity and interdependence of relevant news and information under time pressure is a key trigger for information overload in professionals.
AI enabled recommender systems are designed to help people find valuable items in vast content. However, main-stream news recommenders (e.g., Apple News, Google News) have failed to reduce news overload for business professionals because they are not targeted enough to deliver valuable recommendations for the highly specific, fast changing needs of B2B professionals. A recent survey found that only 32% of C-level executives felt that information delivered to decision makers in their organization is relevant and timely.
Knowledge about B2B professionals’ work and the corporate domain where they operate is critical to identifying useful, actionable and relevant recommendations for an under-served, but important population
We developed, tested and deployed a hybrid AI news recommender system for B2B professionals that models users’ commercial relationships and delivers proactive, highly targeted news recommendations via a simple chatbot UI. The results of this deployment at a global enterprise show that MQ is effective at understanding users’ commercial relationships and making useful recommendations. In particular, incorporating salient domain entities into modeling of user work and the recommendation process yields significantly more useful recommendations.
AI enabled recommendation systems that combine knowledge about the user’s work and about the domain to generate highly-targeted recommendations with minimal user effort have much better potential to improve information overload for B2B professionals. Specifically, news recommendations for specific populations of professionals are an early and profitable area for businesses do deploy hybrid AI systems.
We recently presented the findings of this research into the power of combining machine learning and deep domain knowledge at the Stanford University AI symposium in a paper entitled: Hybrid AI System Delivering Highly Targeted News to Business Professionals
In this analysis, we present how MQ – a hybrid AI news recommender system that uses an explicit model of professionals’ commercial relationships – was able to deliver highly targeted news recommendations via a simple chatbot UI. The paper presents the results from a commercial deployment demonstrate that MQ successfully identifies users’ commercial relationships, makes useful recommendations, and drives high and sustained user engagement. In it, we show that domain-specific, knowledge-aware refinements to user modeling and recommendation generation can improve performance.
