Machine Learning and Technical Debt with D. Sculley Holiday Repeat

Dec 25, 2017

31:55

Originally published November 17, 2015

“Changing anything changes everything.”

Technical debt, referring to the compounding cost of changes to software architecture, can be especially challenging in machine learning systems.

D. Sculley is a software engineer at Google, focusing on machine learning, data mining, and information retrieval. He recently co-authored the paper Machine Learning: The High Interest Credit Card of Technical Debt.

How do you define technical debt?
Why does technical debt tend to compound like financial debt?
Is machine learning the marriage of hard-coded software logic and constantly changing external data?
What types of anti-patterns should be avoided by machine learning engineers?
What is a decision threshold in a machine learning system?
What advice would you give to organizations that are building their prototypes and product systems in different languages?