article thumbnail

Towards optimal experimentation in online systems

The Unofficial Google Data Science Blog

To find optimal values of two parameters experimentally, the obvious strategy would be to experiment with and update them in separate, sequential stages. Our experimentation platform supports this kind of grouped-experiments analysis, which allows us to see rough summaries of our designed experiments without much work.

article thumbnail

To Balance or Not to Balance?

The Unofficial Google Data Science Blog

In an ideal world, experimentation through randomization of the treatment assignment allows the identification and consistent estimation of causal effects. This algorithm is implemented in the SuperLearner R package (Polley & van der Laan, 2014). 2014): 243-263. Eric Polley and Mark van der Laan (2014). 2012): 25-46.

Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Trending Sources

article thumbnail

Themes and Conferences per Pacoid, Episode 6

Domino Data Lab

Spoiler alert: a research field called curiosity-driven learning is emerging at the nexis of experimental cognitive psychology and industry use cases for machine learning, particularly in gaming AI. The ability to measure results (risk-reducing evidence). Ensure a culture that supports a steady process of learning and experimentation.

article thumbnail

Assembly required: 8 myths about knowledge management debunked

CIO Business Intelligence

Prior to Satya Nadella becoming CEO in 2014, Microsoft had a toxic, non-innovative culture known for information and product silos, cutthroat competition through forced ranking of employees, and office politics. It leverages vast amounts of data about customer interactions, purchases, and browsing behaviors to derive actionable insights.