Context and problematic
Our client wants to be aware in real time of the topics that trigger buzz, regardless of target, subject and media type. Therefore, it was necessary to aggregate a very large amount of data through different sources.
After a successful POC, we worked on the development of a platform for daily reporting.
Goals
Our intervention
1 Data Architect, 1 Data Engineers, 2 Data Scientist, 1 full-stack developer
- Definition of the scope and launch of a pilot project to validate the feasibility within 8 weeks
- Implementation of the project architecture on AWS
- Development of analysis algorithms for texts in several languages and images in Python
- Integration of machine learning algorithm
- Development of the visualization application in reactJS and VueJS
Results
Platform has been functional since December 2019 for the business across all structures worldwide !
During the industrialization phase for the customer at group level
Till date, we are working on the analysis of new features such as its e-reputation.
Technical environment
Python, Go, Typescript, react.JS, vue.JS, Node.JS
AWS: S3, VPC, IAM, Cognito, ECS/ECR, Lambda, Glue, RDS, Fargate, Batch, WAF, API Gateway, DynamoDB, ElasticCache, Route53, EventBridge, SageMaker
Elastic Search, Kibana
Docker, Kubernetes, Terraform