For how long is a customer going to use a company’s service? How many product returns should the quality team expect next year? For how many days are hospital beds occupied? 

These are all time-to-event problems with great economical and efficiency impact for their respective sectors. This workshop will introduce participants to survival analysis, a technique originally used in medicine and now employed for analyzing the expected duration of time until any kind of event happens.

During the workshop, participants will be introduced to the basic concepts behind survival analysis. During the hands-on sessions, they will apply those to a customer churn use case and will extract meaningful insights. 

Participants will learn:

• What kind of problems are suitable for survival analysis and what are its advantages compared to classical regression problems;
• The basic concepts behind it, such as the survival and hazard functions, censoring and the concordance index;
• How to apply this on real data with python packages;
• What are the appropriate models for different cases and how to interpret them;
• How to make relevant predictions.

Basic knowledge of python is recommended. Participants need to have a laptop with wireless internet access. Both the code and data used during the workshop will be made available to the participants.