Saturday, October 19, 2013

Five Deadly Sins of Data Science

  1. Cherry picking
  2. Confirmation bias
  3. Data selection bias
  4. Narrative fallacy
  5. Cognitive bias
  6. (Adding one more): Not sharing the raw data AND the algorithms used.
From the Data Science Association via Information Week, for more
Posted by at

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)