Fuzzy Language in Data Science

Picture this: you’re working on the data team of a large retail company. You’ve been building a project to segment customers by various metrics like age bracket, location, buying tendencies, etc.

Then, your manager stops by your desk on the way to a meeting and asks you to figure out who your “best customers” are. As she walks away, you realize that what “best” means isn’t really clear. The biggest spenders? The most frequent buyers? Potential customers with a high chance of spending in the future?

This is a pretty common scenario in data science: you’re assigned a task with “fuzzy” language that can make it difficult to determine how to proceed. In this mission of our Data Analysis in Business course, we’re going to confront that challenge head-on!


  • Learn about the use of nebulous language
  • Learn how to deal with fuzzy language

Lesson Outline

  1. Fuzzy Language
  2. Communication is a Two-Way Street
  3. Dealing with Fuzzy Language
  4. Churned Customers
  5. Aggregate Data by Customer
  6. Ranking Customers
  7. Determining a Threshold
  8. Delivering the Results
  9. Next Steps
  10. Takeaways

Get started for free

No credit card required.

Or With

By creating an account you agree to accept our terms of use and privacy policy.