I've been teaching my daughter multiplication the past two weeks.
Instead of memorizing the 12-by-12 chart, I'm teaching her patterns that she can use with any number (2 * a number is just doubling a number, 4 * is just doubling 2 *, etc).
Once she learns the patterns she can use them all over the place. She'll also see how much of math is just patterns. Both great life skills.
In data analysis like in Repeat Customer Insights, patterns come up a lot.
Some patterns are easy to spot, especially when they are formatted correctly. Seeing a seasonal buying pattern in a cohort report is easy those if the report uses colors and percentages properly. You can spot the diagonal banding easily and see outliers that are off.
Other patterns are difficult to spot for us but easy for a computer. Tracking how the Average Order Value has decreased from last year for new customers but not repeat customers would take a lot of work by a person to find, but it's easy for a computer. The computer just has to be told to look for it and then you can step back and see what it finds.
The nice thing about most data patterns are that the same patterns can be used across a wide range of stores and their data. The pattern still works if your AOV is $10 or $10,000. Learn (or program) it once and it just keep working.
Eric Davis
Market to your customer's timing
Figure out how long customers wait in-between purchases and you have a key component for your marketing timing. This is the basis of the Average Latency metric and Order Sequence Report in Repeat Customer Insights.