Presented By O'Reilly and Cloudera
Make Data Work
Sept 29–Oct 1, 2015 • New York, NY

Machine learning in big data – look forward or be left behind

Bill Porto (RedPoint Global)
2:55pm–3:35pm Wednesday, 09/30/2015
Location: 1 E14
Average rating: **...
(2.80, 10 ratings)

Applying machine learning to big data is something many strive for and few achieve – yet.

Creating models to predict customer response or to segment customer data into set categories are “predictable” use cases. Taking data, discovering what it can tell you, and creating a model and a use for it sound simple enough. It’s a start, but not enough to impact sustainable revenue or cost advantage for your enterprise.

This session will cover the mission-critical questions related to model choice, viability horizon, practical design alternatives, learning from on-the-fence model factors, and opportunities for automating access to changing data and netting-out error and noise.

Bill Porto, senior analytics engineer at RedPoint Global, will discuss why continual, adaptive optimization is the key to maintaining a leadership position in satisfying customer demand. He’ll explain in detail the applicability of machine learning tools with pros/cons for each approach, and discuss how these processes should and can be optimized to predict, segment, and ultimately drive more predictable outcomes from business decisions.

Approaches for populating and tuning your models will also be explored. Through real-world examples and customer use cases, you will learn how to apply predictive modeling and optimization to harness the full power and potential of your data.

This session is sponsored by RedPoint Global, Inc.

Bill Porto

RedPoint Global

Bill Porto is an expert in applying computational intelligence to solve real-world problems across various problem domains. As senior analytics engineer at RedPoint Global, he develops automated business optimization software that incorporates evolutionary optimization, neural networks, and a host of other non-traditional machine learning techniques. An applied mathematician by trade, Bill has created adaptive solutions to dynamic problems for resource allocation, pattern recognition, drug discovery, and logistics scheduling. Before RedPoint, he was president of Natural Selection, Inc. where he received the 2010 FDA Honor Award for his work on their PREDICT automated risk-assessment system.