Member-only story
5 Biases & Fallacies Data Scientists Should Beware of (and How to Avoid Them)
Common mistakes to look out for in your career
Introduction
One of the hardest things about working with data is dealing with the fallacies and biases that plague both the data itself as well as how we interpret the data. Because of the hundreds of biases and fallacies that exist, most of us are guilty of making false conclusions and creating biased models.
In this article, I wanted to talk about 5 of the most common biases and fallacies that all data scientists should look out for and how to actually avoid them.
With that said, let’s dive into it!
Be sure to SUBSCRIBE here to never miss another article on data science guides, tricks and tips, life lessons, and more!
1. Novelty Bias
What is it?
Novelty bias is when customers engage with a new feature or product because it’s new, but not necessarily because they like it or because it’s valuable. For example, if a new button shows up on the YouTube home page, it’s very likely to get a lot of clicks initially because users are curious as to what the button does. When novelty bias is present, it’s likely that the treatment group gets…
