Brinda Thomas, Senior Data Scientist, Tesla
Doing data science for companies that make physical vs virtual products brings entirely new challenges and opportunities. Making the case for sustainability amid a myriad of business and operational goals poses additional challenges. This talk explores the technical, organizational, and business factors that differentiate industrial data science applications from its web- and social- counterparts. In addition, I will examine the unique data management and analytical problems encountered in industrial and manufacturing settings and some useful methods and tools in practice. Finally, I will make the case that the most effective sustainability applications in industrial data science start in the design process rather than in downstream or retrospective analytics.
Brinda Thomas is a data scientist at Tesla Motors, where she is responsible for developing data products, training, and applications of manufacturing process data to improve yield and ensure product quality. She has also worked at GE Software on predictive modeling for financial and smart grid applications. She has a Ph.D. in Engineering and Public Policy from Carnegie Mellon, where she studied building energy efficiency and rebound effects, and a B.S. in Physics from Stanford University.
Slides attached below.
Past talks >