Executive Briefing: Fusing data and design
Data scientists feel naturally comfortable with the language of mathematics, while designers think in the language of human empathy. Creating a bridge between the two was essential to the success of a recent project at an energy company. Tim Daines and Philip Pilgerstorfer detail what they learned while creating these bridges, showcasing techniques through a series of aha moments.
Talk Title | Executive Briefing: Fusing data and design |
Speakers | Tim Daines (QuantumBlack), Philip Pilgerstorfer (QuantumBlack) |
Conference | O’Reilly Artificial Intelligence Conference |
Conf Tag | Put AI to Work |
Location | London, United Kingdom |
Date | October 15-17, 2019 |
URL | Talk Page |
Slides | Talk Slides |
Video | |
One large energy company’s work to optimize natural resource production offers a road map of how you can think through the journey of design and data. In this case, resources were extracted from the ground using a piping system, where small changes in valve settings can impact how much is being pumped from the ground. Business leaders wanted to give the frontline operators data-driven insights to increase production rates—even a tiny increase could result in millions of dollars of revenue. Data scientists feel naturally comfortable with the language of mathematics, while designers think in the language of human empathy. Creating a bridge between the two was essential to the success of this project. Tim Daines and Philip Pilgerstorfer detail what they learned while creating these bridges, showcasing techniques through a series of “aha” moments. Data and design experts met with the end users to understand their thought process in routing the fluid through a maze of pipes in the field and what factors led them to choose one pathway over another. These conversations helped reveal that the algorithms didn’t have to think about the trillions of random combinations of valve settings but instead had to consider the holistic route the fluid could take, simplifying the mathematical engine of the solution. These insights were sufficient to power an optimization solution that, in this simplified space, could create suggestions about pipeline setup that surpassed that of any expert.