loading

Business Impact

  • Automated Production Model Lifecycle Management

  • Improved Operational Efficiency

Customer Key Facts

  • Location : India
  • Industry : Retail and CPG

Problem Context

The client is an Indian consumer goods company that primarily manufactures fashion accessories such as watches, jewelry, and eyewear. They build Machine Learning models on local systems that need to be deployed and configured manually, making the entire process time-consuming and the system unscalable.

Challenges

 

  • Automating using Airflow by leveraging parameter store for around 100 models in production
  • Building a generic template to accommodate over 100 models of different frameworks
  • Rigorous testing of each model’s end-to-end pipeline in development environment before deploying in production environment
Challenges

Technologies Used

Amazon EC2
AWS Lambda
Amazon ECR
Amazon SageMaker
Amazon Systems Manager
Amazon RDS
Amazon S3
AWS CodeCommit
Apache Airflow
Amazon Athena
Amazon Glue
Amazon QuickSight
Amazon API Gateway

Automating the deployment of over 100 models in client’s environment by leveraging Airflow DAG Scripts

Solution

Quantiphi is helping the client in the orchestration of training, evaluation, and deployment of over 100 models running on SageMaker by leveraging Apache Airflow. Once each model is deployed, the Production Model Lifecycle is such that the scoring, evaluation, and retraining of the model is automated. Quantiphi is also helping the client in the visualization of the performance of the deployed models using Amazon QuickSight and Amazon Athena.

Result

  • Reducing the manual efforts of for set-up and configuration
  • Generalized templates for deployments with ease
  • Smart insights and Visualization on the performance of models

Looking for similar project?

Let's Talk

Get your digital transformation started

Let's Talk