Video: Extreme-scale Data Science Using Spark
At the Spark Summit in Brussels, MediaMath’s SVP of Data Science, Prasad Chalasani, gave an invited keynote talk, Extreme Scale Ad-Tech at MediaMath with Spark and Databricks.
MediaMath’s demand-side platform responds to over 200 billion ad-opportunities daily, and leverages massive amounts of data to power smarter digital marketing. We use Spark heavily both in production and R&D to develop innovative, proprietary, and scalable solutions to multiple large-scale data problems, such as:
- Training Machine-learning models for predicting conversion probability given an ad-impression
- Measuring causal effectiveness of advertising using randomized tests
- Estimating audience reach for specified targeting criteria.
- Finding deviceIDs belonging to the same user based on possibly noisy external deterministic information.
- Attributing clicks and conversions.
- Estimating win-rate as a function of bid-price and impression features.