With today’s massive global adoption of personal computers, smartphones, tablets, and the emerging class of devices, we live in a time of unprecedented device proliferation. This gives rise to very fundamental challenges around the fragmentation of consumer identity. The big Internet giants of Google, Facebook, etc. have an inherent advantage in solving for this through their first-party data of made up of a stateful, logged-in base of user information. This creates an inequity across the digital and Internet economy in the ability to provide seamless experiences and solutions from understanding consumer identity. This talk will address how machine learning and data science best-practices can solve for this identity capability, and how it can be done in a privacy-safe and data-safe manner, with high precision and at massive scale.

The talk focuses on the algorithms developed at Drawbridge that process a massive scales of data in near-real-time spans to solve for a single user’s identity across different domains, while still protecting consumer anonymity.