Challenge
The company needed to achieve a higher customer acquisition rate among customers with a higher likelihood of discontinuing prepaid mobile service. Previously, specific offers were made to them based on their churn propensity level (High, Medium, and Low).
In the presented solution, there was no way to determine if that offer was the most suitable for each customer. In other words, customers with a High churn propensity were offered the offer designated for that group – is that the best offer for the group? There was also no way to know whether these offers were indeed the most appropriate for that specific customer, meaning: does the customer in the group actually want that offer or a different one? Lastly, what offer would the customer desire and be profitable for the company?
The main obstacle in doing this was how to create a model that could effectively predict what the customer might choose based on past decisions and within a specific context (such as available balance, time of offer, behavior, etc.).
Another challenge was how to increase customer monetization. This meant that while the first personalized offer had the highest chance of being selected, it might not be the most profitable one. Perhaps the second personalized offer, with a higher chance, could be more profitable.
Why AWS
For several years, CWP has used AWS services to store its data in data lakes, as well as for conducting analytics, predictive modeling, and visualizations. The experiences of the client and Strata with AWS services built confidence in their performance, deployment speed, and convenience. Implementing SRE on this platform was ideal because it did not require migrating to any services outside of AWS, as the entire SRE-MLOps service environment and development run on AWS platform services.
Why the Customer Chose the Partner
Strata has collaborated with CWP on various projects, including developing different predictive models for both fixed and mobile segments, as well as analytics to generate valuable insights for the business. Additionally, several dashboards were created using QuickSight to visualize campaign effectiveness and other solutions. In other words, Strata possesses extensive knowledge of the potential and development within the AWS environment, and the client also trusts Strata and has data available within AWS.
Partner Solution
The solution deployed by Strata involved creating a framework that compiles data from three sources: Interactions, User Data, and Offer Data. Using this information, a model was trained with AWS Personalize, followed by a weighted ranking to prioritize monetization. Based on these results, personalized campaigns were developed to visualize conversion outcomes. This entire process runs automatically twice a week, utilizing the most current data to provide near-real-time training information.
HL Architecture
The architecture begins with data from various sources, categorized into three domains: interactions, user information, and product details. This data is pre-processed and used in Sagemaker, also leveraging AWS Personalize services, with inferences stored in an S3 bucket. These inferences are then accessed by Lambdas to trigger campaigns sent to users. Logging services are also employed to monitor each step of the process.
Results and Benefits
The solution is fully automated and requires no human intervention. It is also simple to replicate for other markets or campaigns, with very short development time. As a parameterized solution, it can easily be adjusted if there is a need to change parameters like the number of offers or the time window for training, it can be easily adjusted. The runtime of the entire process is approximately 2 hours to run.
Next Steps
The next steps involve continuously improving the model as more cases with additional interactions provided by SRE are trained, since it is a model that learns from its past recommendations. Progress is also being made in implementing this solution in other customer campaigns.
