all AI news
Goodhart’s Law and the Dangers of Metric Selection with A/B Testing
Feb. 25, 2022, 4:12 a.m. | Graham McNicoll
Towards Data Science - Medium towardsdatascience.com
The surprisingly counterintuitive problems of choosing metrics (and how it relates to cobras)
Photo by NIvedh P on UnsplashExperimentation has many parts: choosing the hypothesis, implementing the variations, assignment, results analysis, documentation, etc, and each of these can have their own nuances that make it complicated. Usually choosing the metric (or metrics) that determines if your hypothesis is correct is straightforward. However there are some situations where choosing metrics can be problematic, and surface classic issues of Goodhart’s law. …
a-b-testing a/b testing b testing dangers data analysis data science law metrics statistics testing
More from towardsdatascience.com / Towards Data Science - Medium
Dissolving map boundaries in QGIS and Python
1 day, 1 hour ago |
towardsdatascience.com
Create an A.I. Driven Product with Computer Vision and ChatGPT
1 day, 14 hours ago |
towardsdatascience.com
Deep Dive into LlaMA 3 by Hand ✍️
1 day, 19 hours ago |
towardsdatascience.com
On handling precalculated hierarchical data in Power BI
1 day, 20 hours ago |
towardsdatascience.com
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne