Abstract: 

Differential privacy is making headlines thanks to the pioneering work of companies like Apple and Google. It is now being used by companies of all sizes to provide data privacy guarantees. It is no secret that machine learning models can memorize (overfit) training data and that through carefully crafted adversarial inputs machine learning models can be subverted by an attacker. This talk will explain the core concepts of differential privacy, a potential solution to such threats. It will also share a behind the scenes look at how Bluecore, a SaaS commerce decisioning platform, is exploring its use to improve predictive model performance, reduce sales friction, and accelerate competitive advantage from a proprietary dataset.

Bio: 

Zahi is the Director of Data Science at Bluecore where he leads a team of engineers and data scientists that help marketers discover their best customers and keep them for life. The focus of his undergrad and master’s degrees was digital signal processing. During his PhD his focus shifted to machine learning and persisted during his postdoctoral fellowship where he built a system to detect mood symptoms in bipolar patients’ cell-phone conversations.