Identifying potential customers based on their Rank and Value

Question

I have a dataset which has demographic data available for a list of new customers. the data does'nt include transaction data of the customers.

I want to identify the top 100 potential customers among these customers. Im aware that we can make use of clustering to segment these customers.However, I have two more variables in my data which are Rank and Value.

What approach should be taken when rank and value of customers are given.How do we interpret the clusters given these 2 variables.

Need some guidance on this

Answer 1

Do you have some data on past clients ? For example, do you have a dataset with past clients Rank and Value, and a variable indicating if the client was good or not (binary variable 1 if the client is good and 0 if it's bad, or a variable to use as indicator, like profit done on the client for example).

If you have such a thing, your problem is a basic classification problem, where your threshold is not 0.5 (the probability you want to be "Good Client" is not 0.5, as it is on default cases), but where you just select the 100 customers with the best probability (closer than 1).

If you don't have such dataset, and such variable indicating if the client was good or bad, based on what you know from the past, then you can't create a model since you don't know how to train it.