Segmenting your customer base to improve your marketing is powerful but you can do it too early.
Splitting a small group of people into even smaller groups can mess with the statistics too much and get you odd results.
A good rule of thumb I use is to make sure each group includes least 100 people. More is better.
For example, if you want to split customers into one-time and repeat customers, you'll need to make sure each group has at least 100 people in it. You'll have many more one-time customers so your repeat customer group will be the limiter. By the time you reach 100 repeat customers you could have 500 one-time customers in that group.
There are ways to split segments equally top avoid this lopsided affect.
With RFM you split your customer base into 5 equal sized groups. To keep the 100-person rule of thumb that means you'd need 500 customers for RFM to be effective.
You can also do something more simple than RFM by splitting your customer base in half or a third. Two equal sized groups would then need only 200 customers, three equal sized groups would need 300.
How you decide to split each segment is up to you and your goals.
RFM and similar algorithms like to use how much a customer has spent or how frequently they've ordered. Those can be done relatively easy with a customer export, spreadsheet program, and finding the median.
Make sure to keep the 100-person rule of thumb in your head. It's not perfect and there are exceptions but if you're working with a small customer base it should be good enough to have a noticeable impact.
And if you want help to do the segmenting, Repeat Customer Insights comes with different analyses and algorithm that will automatically segment your customers for you. Some work well with as few as 500 customers.
Use cohorts to find out who the best customers are in your Shopify store
Repeat Customer Insights will automatically group your customers into cohorts based on when they first purchased. This will let you see how the date customers bought would impact their behavior.