topic Re: Customer Value Segmentation in SAS Enterprise Guide

Customer Value Segmentation

onimisi_esho — Wed, 04 Dec 2019 09:10:59 GMT

Hi, Please I am trying to do a segmentation analysis by grouping customer's into different segments by their revenue. The segments are Top 1%, Next 4%, Next 15%, Next 30% and bottom 50%.

Please what is the best approach to this.

I thought about using percentiles.

Re: Customer Value Segmentation

PeterClemmensen — Wed, 04 Dec 2019 09:36:16 GMT

@onimisi_esho hi and welcome to the SAS Community 🙂

This can be done in a few different ways. Have you read this?

https://blogs.sas.com/content/iml/2019/08/07/essential-guide-binning-sas.html

Re: Customer Value Segmentation

onimisi_esho — Wed, 04 Dec 2019 10:05:56 GMT

hi @PeterClemmensen ,

Thanks four response.

The quantile binning option seems to be the closest option to my problem. I am relatively new to SAS.

My data is on a table and I wish to output my result in the same table.(See Photo) My intended output is in yellow.

How will i go about this incorporating the function considering i will be writing an SQL statement.

Re: Customer Value Segmentation

Reeza — Wed, 04 Dec 2019 18:42:54 GMT

Only by revenue? If so, that's more classification than segmentation as segmentation usually has multiple variables. If you're looking at just one variable and specific percentiles start with PROC RANK and GROUP=100. That will give you the percentile for each value and you can then create your groups as desired.

proc rank data=sashelp.cars out=want groups=100;
var mpg_city;
rank mpg_city_rank;
run;

*see distribution of ranks;
proc freq data=want;
table mpg_city_rank;
run;

This will create the ranking variables and you can then filter - 0 is lowest and 99 is the highest usually.