Welcome back to my series on predicting customer lifetime value, which I call "Everything Other Tutorials Miss." In Part 1, I covered the often estimative phase of *historical* CLV analysis and what can already be done with such seemingly backward information. Next, I presented use cases for the tone of CLV *forecasting*, going beyond the typically limited examples seen in other posts on this topic. Now it's time for the practical part, including everything I've learned while working with the data science team and real data and customers.

Once again, there is too much juicy information to fit into a single blog post without turning it into an odyssey. So today, I will focus on historical CLV modeling. I will cover the silly simple formula, cohort analysis, and the RFM approach, including the pros and cons I discovered for each. Next, I will do *the same*. And I will wrap up the entire series with best practices learned by data scientists on how to perform CLV correctly.

Sounds good? Then let's take a look at the historical CLV analysis methods and the advantages and "Gotchas" you need to know.

## Method 1: Silly Simple Formula

Perhaps the simplest formula is based on three elements: how much customers typically purchase, how often they shop, and how long they maintain loyalty:

For example, if the average customer spends €25 per transaction, makes two transactions a month, and maintains loyalty for 24 months, then CLV = €1200.

We can make this a bit more sophisticated by considering margins or profits. There are several ways to do this.

## Silly Simple Formula V1: Product-Specific **Margin**

Here, we calculate the average margin per product for all products in inventory, and then multiply this number by the silly simple formula result to generate the average customer lifetime *margin*.