Junk Charts
  • About
  • RSS
  • Posts by Year
  • Posts by Keywords
Sign in Subscribe

Models

Apparently Hollywood does not recycle action-movie plots. The data said so, so it must be right
Bias

Apparently Hollywood does not recycle action-movie plots. The data said so, so it must be right

It pains me to think how many people have used these keywords to build models.
Read More
Algorithms

If you are using Facebook Ads split testing (A/B testing), stop fooling yourself

Kaiser Fung, founder of Principal Analytics Prep, and former director of Applied Analytics at Columbia University, explains why you can't run proper A/B tests on Facebook
Read More
Counting is hard, especially when you don't have theories
Big Data

Counting is hard, especially when you don't have theories

Exploring the data about movies, uncovering data issues
Read More
Pre-processing data is not just about correcting errors
Algorithms

Pre-processing data is not just about correcting errors

Exploration of IMDB rating data, by Kaiser Fung, founder of Principal Analytics Prep
Read More
Good models + Bad data = Bad analysis
Aggregation

Good models + Bad data = Bad analysis

Example showing how to diagnose bad data in data science models
Read More
How do you react to a probability forecast?
Current affairs

How do you react to a probability forecast?

There is a healthy debate going on about last night's
Read More
← Newer Posts Page 2 of 5 Older Posts →
Junk Charts © 2025
  • BOOKS
  • COURSES
  • PRESS
  • CONSULTING
  • COACHING
  • CONTACT
Powered by Ghost