This Guidance leverages Machine Learning (ML) techniques to build churn prediction models that identify subscribers who are high risk to churn and their key drivers. This can help Communication Service Providers to personalize offerings and retain subscribers.
Architecture Diagram
Step 1
Telecom data is collected into an Amazon Simple Storage Service (Amazon S3) object storage bucket. Data includes call data records (CDRs), billing data, and data from customer care.
Step 2
A churn model is trained on the labelled data set, tested and tuned, then deployed using Amazon SageMaker.
Step 3
For every churn inference event, Amazon SageMaker Clarify identifies the important feature to the model to determine churn likelihood.
Step 4
Churn model predictions and explainability reports are exported to an Amazon S3 bucket by using an AWS Lambda function.
Step 5
Amazon Quicksight visualizes the model and explainability data, allowing for interactive analysis and identification of trends and decision support of who to send a churn retention offer. Amazon Athena is used by Amazon QuickSight to access the Amazon S3 data.
Step 6
The telecom analyst can then decide how to act on the insight and can use Amazon Pinpoint to send out subscriber retention offers.
Step 7
Telecom applications can also incorporate near real-time churn prediction by calling the SageMaker hosting endpoint.
Step 1
Telecom data is collected into an Amazon Simple Storage Service (Amazon S3) object storage bucket. Data includes call data records (CDRs), billing data, and data from customer care.
Step 2
A churn model is trained on the labelled data set, tested and tuned, then deployed using Amazon SageMaker.
Step 3
For every churn inference event, Amazon SageMaker Clarify identifies the important feature to the model to determine churn likelihood.
Step 4
Churn model predictions and explainability reports are exported to an Amazon S3 bucket by using an AWS Lambda function.
Step 5
Amazon Quicksight visualizes the model and explainability data, allowing for interactive analysis and identification of trends and decision support of who to send a churn retention offer. Amazon Athena is used by Amazon QuickSight to access the Amazon S3 data.
Step 6
The telecom analyst can then decide how to act on the insight and can use Amazon Pinpoint to send out subscriber retention offers.
Step 7
Telecom applications can also incorporate near real-time churn prediction by calling the SageMaker hosting endpoint.
Well-Architected Pillars
The AWS Well-Architected Framework helps you understand the pros and cons of the decisions you make when building systems in the cloud. The six pillars of the Framework allow you to learn architectural best practices for designing and operating reliable, secure, efficient, cost-effective, and sustainable systems. Using the AWS Well-Architected Tool, available at no charge in the AWS Management Console, you can review your workloads against these best practices by answering a set of questions for each pillar.
The architecture diagram above is an example of a Solution created with Well-Architected best practices in mind. To be fully Well-Architected, you should follow as many Well-Architected best practices as possible.
-
Operational ExcellenceRead the Operational Excellence whitepaper
Telecom data is used to identify the churn propensity of a telecom subscriber. This aligns with business objective. A custom machine learning (ML) model is trained in the cloud on customer data to determine churn. Results of the model and feature importance is visualized in QuickSight to help business analysts identify trends to provide decision support of who to approach with a customer retention offer.
-
SecurityRead the Security whitepaper
All data is encrypted both in motion and at rest. Encrypted Amazon S3 buckets store data and SageMaker can only access that data by using the VPC (and not the internet). Training is done in secure containers and the results are stored in encrypted S3 buckets.
-
ReliabilityRead the Reliability whitepaper
SageMaker hosting is used to server the trained model, which takes advantage of multiple Availability Zones and elastic Scaling groups.
-
Performance EfficiencyRead the Performance Efficiency whitepaper
Serverless technology is used where possible. SageMaker Endpoints can scale up and down as needed to ensure the minimum number of instances needed are running.
-
Cost OptimizationRead the Cost Optimization whitepaper
SageMaker endpoints can scale up and down as needed to ensure the minimum number of instances needed are running. Instance sizes are measured by using SageMaker Instance Recommender to make sure costs are minimized.
-
SustainabilityRead the Sustainability whitepaper
By extensively using managed services and dynamic scaling, we minimize the environmental impact of the backend services. All compute instances are sized to provide maximum utility.
Implementation Resources
A detailed guide is provided to experiment and use within your AWS account. Each stage of building the Guidance, including deployment, usage, and cleanup, is examined to prepare it for deployment.
The sample code is a starting point. It is industry validated, prescriptive but not definitive, and a peek under the hood to help you begin.
Related Content
[Title]
Disclaimer
The sample code; software libraries; command line tools; proofs of concept; templates; or other related technology (including any of the foregoing that are provided by our personnel) is provided to you as AWS Content under the AWS Customer Agreement, or the relevant written agreement between you and AWS (whichever applies). You should not use this AWS Content in your production accounts, or on production or other critical data. You are responsible for testing, securing, and optimizing the AWS Content, such as sample code, as appropriate for production grade use based on your specific quality control practices and standards. Deploying AWS Content may incur AWS charges for creating or using AWS chargeable resources, such as running Amazon EC2 instances or using Amazon S3 storage.