Skip to main content
dstillery dstillery

Marketing Science Institute

Melinda Han Williams will discuss the promises and pitfalls of infusing a historically intuition-based industry with rigorous machine learning for targeting and measurement. What are the new realities of an environment where 100 billion advertising opportunities are sold daily in real-time auctions? These include high volume data streams of around 30 billion daily consumer touch points, low latency requirements on scoring and automated bidding (within100 milliseconds), and adversarial modeling in response to advertising fraud and bots. Most challenging, however, are incentive misalignments and measurement issues in the advertising industry and the paradox of big data and predictive modeling: You never have the data you really need.

Melinda Han Williams
Lead Data Scientist