0
$\begingroup$

I am working on a project to provide recommendations to the marketing team to launch effective campaigns. The dataset I have has data on existing customers, their demographic and billing details as well as tenure, plan and existing products that they have subscribed to. The task is to increase adoption on one of the particular products - PROD_B.

Can someone help me understand the approach? I understand that I need to build a model to predict probability of buying the product and then sort it in descending order to get the most likeliest customer, most likely using content-based filtering approach.

Can someone advise me on how I can approach this problem and any other methods that might work?

Following is the data dictionary:

Feature Definition

CUSTOMER_NO  ID of a customer

DEVICE  Type of Device 

CITY    City of the customer

STATE   State of the customer

TENURE  Tenure

PRICE   Price

PROD_A  Boolean value indicating if the customer has product A

PROD_B  Boolean value indicating if the customer has product B

PROD_C  Boolean value indicating if the customer has product C

PROD_D  Boolean value indicating if the customer has product D

PROD_E  Boolean value indicating if the customer has product E

SEGMENT Name of segment

LOCALITY    Name of locality

BILLING_6_MONTHS    Average billing amount for last 6 months

Its not the exhaustive list, but other features are similar to the ones above.

$\endgroup$

1 Answer 1

0
$\begingroup$

Market basket analysis [1, 2] will let you learn association rules and derive their support, confidence and other metrics to guide your search for the most valuable associations.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.