DATA ARE AT THE CENTER OF DATA SCIENCE: MY TAKE ON WHAT EVERYONE SHOULD KNOW ABOUT DATA

Arne Bathke

Keywords: Bias, Data, Paradoxa, Statistics

Short Summary:

We will review the essential workflow ADD-PIC that underlies sensible statistics and data science, and much of AI, and then discuss in detail the important role of data in this workflow, spiced with some typical mistakes and pitfalls, generated, among others, by biases and seemingly paradoxical situations.
ADD-PIC is: Asking sensible, relevant questions; Data acquisition; Description and quality check; Prediction and generalization; Interpretation; Communication
Based on this, we will propose some key points that students need to know about the concept of data in order to do statistics and data science in a sensible way, and to understand better the possibilities and limitations of AI.

Topic Area: Data and Problems

Presenting Author: Arne C. Bathke

Presentation Type: Short Presentation (ca. 20 min)

Submission Number: 11