Torch: Season 1, Episode 4

Can data scientists foresee the future? – Wrong predictions & their benefits

Can data scientists predict the future? As a data scientist, I know that most predictions are wrong. However, there is some truth to this myth. In “Torch”, our new data science series, I will show you how wrong predictions can still be useful for statistical forecasts.


Download takeaway

In my “Torch” episode, you will learn:

  • How you can calculate customer churn using probabilities.
  • Why these probabilities, which are false at the individual level, are nevertheless valuable overall.
  • How these probabilities help your company target customers.

Want to see this on a real-life example? In my takeaway, I show you how we used “wrong” assumptions to forecast a company’s customer churn.

Hi there, my name is Sacha, and I am a data scientist at Trivadis – Part of Accenture. I come from the realms of statistics – that is the subject I got my Master’s degree in. Thus, I am interested in inference, optimization methods and business analytics. My heart does not only beat for data science, however: for 9 years, I have played professional tennis, first in France and then in the US. Originally from Paris, I am now based at Lausanne. 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

Using «wrong» assumptions to make predictions about the future – that is what my team and I did for a client from the public sector. How we estimated their future customer churn using machine learning and implemented this into a business intelligence solution? In this takeaway, you will find concrete tips for your own customer churn prediction use case.

Download takeaway

Your contact