Torch: Season 1, Episode 2

Is data science magic? – CRISP-ML & iteration

Is data science a mysterious process in which raw data is turned into gold in a way that cannot be understood? As a data scientist, I am often confronted with this myth. But is it actually true? In “Torch”, our new data science series, I will show you a typical data science procedure, called CRISP-ML, so you can make up your own mind.


Download Takeaway

In my “Torch” episode, you will learn:

  • How CRISP-ML works and how you can use it for your own data science project.
  • What business questions you have to ask before even starting the project.
  • Why iteration is at the core of data science.

Want to see this on a real-life example? In my takeaway, I show you how we apply CRISP-ML for customers and how you too can make data science projects fly.

Hi, I'm Lev, and I've been a data scientist at Trivadis – Part of Accenture for over seven years. When I'm not shooting videos, I support a wide variety of companies in developing and implementing data-driven solutions. I also teach data science and data analytics at the Haute École Arc in Neuchâtel. I am known for always questioning things and uncompromisingly looking for the best approach in a project. And when I'm not working on algorithms and statistics? Then I like to kill monsters and save the world on my video game console. PS: Did you enjoy my “Torch” episode? Then let’s get in touch – I would love to pass the torch and discuss the world of data science further!

What I share with you

To obtain more accurate forecasts of product demand, we used CRISP-ML, a standard procedure for data science projects, at a consumer goods company. What challenges did we encounter and how did we solve them? In this takeaway, you'll get concrete tips on how to make your own data science project a success.

Download takeaway


Microsoft Analytics

Is data the new oil? – Abundance & value creation

Your contact