ELI5: Explain Like I'm 5

Yule–Simon distribution

Imagine you have a toy box with different types of toys. Some toys are very popular and you have a lot of them, while others are rare and you only have a few. The Yule-Simon distribution is a way to understand how likely it is for a specific type of toy to be picked randomly from the toy box.

Imagine you want to pick a toy at random from the box, but you don't know which one you are going to get - it could be any toy. If you pick a toy from the box, the chance of getting a popular toy (one that you have a lot of) is much higher than getting a rare toy (one that you only have a few of).

The Yule-Simon distribution is a mathematical way to represent this idea. It tells us that the likelihood of picking a specific type of toy, such as a popular toy, is proportional to the number of times that toy has already been picked. This means that the more popular the toy is, the more likely it is that it will be picked again.

For example, if you have a lot of toy cars in your box, and you pick toy cars randomly, you are more likely to pick another toy car than a different type of toy. This is because there are more toy cars in the box than any other type of toy.

In summary, the Yule-Simon distribution is a mathematical way of understanding how likely it is to pick a certain item from a group of items, based on how many times that item has been picked in the past.