Abstract: 

As enterprise demand for intelligent, data-driven decisions grows, so do the complexity and urgency of the problems that data scientists are asked to tackle. Machine learning (ML) enables data scientists to leverage data to build models for classification, forecasting and prediction. However, after forecasting, for example, machine outages, the business may also need to decide on how best to schedule repair crews. Or after predicting customer churn, how best to allocate marketing budget to stave off churn. In each case, the later problem is best solved with decision optimization (DO) models. But DO requires very different expertise than ML, and the combination is even more challenging. This session will describe new tools for data scientists to dramatically simplify solving ML+DO challenges by automatically generating ML+DO model pipelines. We’ll also describe how next generation semantic feature discovery technologies that will further improve upon these models by automatically harvesting domain knowledge from python code, web tables, documents and related data sets.

Bio: 

Dr. Lisa Amini is the Director of IBM Research Cambridge, which is also home to the MIT-IBM Watson AI Lab, and of IBM's AI Horizons Network. Lisa was previously Director of Knowledge & Reasoning Research in the Cognitive Computing group at IBM’s TJ Watson Research Center in New York, and she is also an IBM Distinguished Engineer. Lisa was the founding Director of IBM Research Ireland, and the first woman Lab Director for an IBM Research Global (i.e., non-US) Lab (2010-2013). In this role she developed the strategy and led researchers in advancing science and technology for intelligent urban and environmental systems (Smarter Cities), with a focus on creating analytics, optimizations, and systems for sustainable energy, constrained resources (e.g., urban water management), transportation, and the linked open data systems that assimilate and share data and models for these domains. She earned her PhD degree in Computer Science from Columbia University.