Stashed ideas - Deepstash

🚀

Stashed ideas

16 STASHED IDEAS

First why, then how

Most people approach data the wrong way: They start with a data set, then use their favourite tools and techniques on it. This produces a narrow set of unsurprising results.

When we want to gain knowledge from the data, we should first do some thinking. Before we can answer how we first need to ask why. But this can be surprisingly challenging. The answer is to have a structure to think through all the aspects of a problem.

1

STASHED IN:

2

Thinking With Data is not about how to do data analysis but about first working out what the problem is that you're trying to solve.

STASHED IN:

0 Comments

Polynomial regression
  • Polynomials are algebraic expressions consisting of variables and coefficients.
  • Polynomial regressions are the most used in machine learning.

Polynomial regression is a unique case of linear regression:

  • You fit a polynomial equation on the data with a curvilinear relationship between the independent variable x and the dependent variable y. 
  • It is modelled as an nth degree polynomial.

STASHED IN:

4

STASHED IN:

0 Comments

Data leaders are more productive
  • They develop twice as many new products as lagging organizations. 
  • They're almost twice as likely to say their data-fueled product innovation has let them enter new markets and increase customer wallet share. 
  • They even have increased employee productivity by nearly twice as much as competitors.
  • Data leaders are nearly twice as likely to be directly monetizing their data.

4

STASHED IN:

23

STASHED IN:

0 Comments