Data science thinking refers to the perspective on the methodologies, process, structure, and traits and habits of the mind in handling data problems and systems [1]. It is the thinking in data science that drives the emergence, development, revolution, and formation of data science as an independent discipline and science.
Understanding the concept of “data science thinking” should include but also extend beyond relevant concepts such as “statistical thinking”, “mathematical thinking”, “creative thinking”, “critical thinking”, and more recently “data
analytical thinking”:
- Thinking in science: Including scientific vs. unscientific thinking, creative thinking vs. logical thinking, and critical thinking, creative thinking, logical thinking and lateral thinking;
- Different views of data science: Including a statistical view of data science, a multidisciplinary view of data science, a data-centric view of data science, and a complex system view of data science;
- Data science as a complex system: A systematic view of data science problems, complexities in data science systems, and data characteristics and complexities;
- Data science thinking patterns: Including various design patterns, learning patterns, and algorithmic paradigms for data science;
- Critical thinking in data science: Including ”we do not know what we do not know”, data-driven scientific discovery, and various data-driven analytical, learning and design patterns and mechanisms.
 |
|
