Propensity score predictor helped our client predict the customers likelihood to purchase a product
Client is a leading e-commerce company selling baby nutrition products. They want to leverage the user’s website behavior.
Current State
-
The client runs various marketing campaigns online and their marketing team would like to have information on their customer profile.
-
The client can then run targeted marketing campaigns to the selected customer which matches their profile
Gaps
-
Absence of a proper mechanism to perform customer profiling
-
Lack of real-time data
-
Absence of a proper solution to consume the data.
Our Approach
-
Ameex developed a solution which extracted data from Google Big Query and stored in Cloud Storage in a structured manner. The analytical layer consists of the model to generate the propensity score, which indicates the likelihood of a customer to purchase the product. This also gives the flexibility to run targeted campaigns to appropriate groups of customers.
-
Data from Big Query is fetched and moved to Google Cloud Storage
-
Dask Parallel processing handles data processing tasks like handling missing values, categorical variables etc…
-
Last 30 days data was taken and feature engineering was performed on it
-
Model is developed using LighGBM and trained using Cross-validation to prevent overfitting.
-
Features: This application includes
-
Option to enter the customer Number and view the propensity score.
-
Option to view the list of customers within a specific score range
Business Impact
-
A solution which gives the propensity score and determines the likelihood to purchase a product
-
An easier consumption mechanism which uses real time data of enrolled and non-enrolled users
Want to learn more about how we have helped our clients with their analytics journey? let’s connect!