In 2019, VentureBeat predicted 87%+ of data science projects won’t make it into production. Countless other studies show how large data-driven initiatives from analytics to data science and AI tend to fail at a rate of 80% or higher—despite ongoing and sizable investments in technology and data. Can product design leaders and UX professionals help fix this, particularly at the enterprise level? Your executives are worried about having an AI strategy. Data scientists worry about getting their models to be as accurate as possible, having the right data, and tons of it before they can even do anything. Where is the customer in all of this? Who exactly is the customer of a “predictive model”? How do we measure success in this context? If business value is dependent on specific users engaging successfully with a model, decision support application or data product, then teams must design these solutions around the people using them—not the data or technology. Design leaders inherently get this, but what’s unique about creating valuable data-driven products and solutions? How are traditional analytics products different than those that generate probabilistic outputs from new techniques such as machine learning? And where does data visualization fit in? If you lead UX at a large enterprise, AI as a strategy is likely on your executive roadmap. However, your executive leadership, particularly if you’re at a non-digital native company, may not even know exactly what AI is, what’s possible, and most importantly how they can leverage it to produce new customer-facing experiences, services, or products. Designer leaders and UX professionals can help, but it means looking at data as “the new pixel,” and understanding what it means to add value when working in this medium, and how UX+Data Science may become just as important as the UX+Product Management relationship.
Attended this talk? Fill out the Session Survey!
