The Analytics Power Hour #269: The Ins and Outs of Outliers with Brett Kennedy
34 snips
Apr 15, 2025 
Brett Kennedy, a freelance data scientist and author of 'Outlier Detection in Python,' delves into the nuances of outlier detection methods. He compares identifying outliers to obscenity, noting the challenges of definition and detection. The discussion spans techniques such as z-scores and the Median Absolute Deviation, emphasizing the importance of context in data analysis. Kennedy also highlights the human touch needed in distinguishing significant anomalies from normal variations, showcasing the interplay between technology and human insight in deciphering data.
AI Snips
Chapters
Books
Transcript
Episode notes
Auditor Software for Outliers
- Brett Kennedy developed outlier detection software for financial auditors who needed to identify unusual transactions efficiently.
- The software targeted millions or billions of transactions to highlight those most worth checking for errors or fraud.
No Absolute Outlier Definition
- There is no absolute definition of an outlier; context and interpretation by analysts matter greatly.
- Something statistically unusual might not be interesting or useful without domain knowledge.
Credit Card Fraud Alert Story
- Val Kroll shared a personal credit card fraud alert story where she was mistakenly flagged for a purchase.
- This illustrates the challenges and improvements in fraud detection systems over time.