Case Study

Achieving Exceptional Accuracy of Over 90% in Content Suggestions for an EdTech

Download the Case Study
Industry 

EdTech

Expertise 

Amazon SageMaker, Amazon Bedrock, Amazon S3, Amazon OpenSearch, Amazon Translate, Amazon Comprehend

Offerings/solutions 

Empowering Creativity with 90%+ Accuracy and Zero Human Intervention in Content Generation

About the Client

An AI-powered EdTech writing and publishing platform has emerged as the world’s leading creative writing platform for children. This innovative platform enables students from classes 1 to 12 to learn creative writing, publish their books online, and sell printed-on-demand books on their website and Amazon.com with a single click. It makes storytelling accessible and exciting for children worldwide.

Highlights

90% accuracy

High Accuracy and Efficiency

Zero Human Intervention

Remarkable Content Creation

Efficiency and Ease of Use

Amazon SageMaker Jumpstart foundation model

The Challenge

The client’s platform enables young authors to create literary works through creative writing, but many users face challenges organizing their thoughts, leading to unfinished books. They wanted CloudThat’s help, and we introduced a custom model to offer tailored recommendations whenever users encounter difficulties in book writing, creative writing, or thought processing.

Solutions

• Client data, stored in CSV format in an Amazon S3 bucket with default encryption, ensures security and integrity.
• Separate AWS IAM user creation for developers in the delivery group ensures effective access and permission management.
• Raw data undergoes thorough preprocessing using Amazon SageMaker to ensure accuracy and consistency, including cleaning inconsistencies, filling missing values, and removing irrelevant information.
• Refined data is stored back in Amazon S3 post-preprocessing for model training.
• GenAI/ML capabilities aid in selecting the most suitable foundation model for text generation tasks, trained using Amazon SageMaker with adjusted hyperparameters.
• Trained model artifacts are automatically stored in Amazon S3 and registered in the model registry for easy access.
• Seamless deployment of the model as a real-time endpoint using Amazon SageMaker facilitates easy integration with applications for real-time response generation.
• AWS Lambda function preprocesses data before calling the endpoint, ensuring tailored responses via REST API to the front end.
• Amazon EventBridge and Amazon CloudWatch monitor and log SageMaker endpoint activities for smooth and efficient system operation, promptly addressing any issues to maintain optimal performance.

The Results

The platform optimizes content creation with meticulously trained models, achieving over 90% accuracy in recommendations while streamlining processes through Amazon SageMaker, ultimately enhancing user experience with minimal human intervention.

Download the Case Study

AWS Partner – Data Analytics Services Competency

Pioneering Data Analytics space by being an AWS Partner – Data Analytics Services Competency.

Learn more

An authorized partner for all major cloud providers

A cloud agnostic organization with the rare distinction of being an authorized partner for AWS, Microsoft, Google and VMware.

Learn more

A house of strong pool of certified consulting experts

150+ cloud certified experts in AWS, Azure, GCP, VMware, etc.; delivered 200+ projects for top 100 fortune 500 companies.

Learn more

Get The Most Out Of Us

Our support doesn't end here. We have monthly newsletters, study guides, practice questions, and more to assist you in upgrading your cloud career. Subscribe to get them all!