AWS Machine Learning Specialty (AWS) case studies
AWS Machine Learning Specialty · Put your knowledge to work in context.
The AWS Certified Machine Learning – Specialty credential is an advanced certification for practitioners who build, train, tune, deploy, and operate machine learning workloads on AWS. It suits data scientists, ML engineers, and cloud architects who already know the fundamentals of statistics, model evaluation, and at least one ML framework, and who now want to prove they can make those skills work inside the AWS ecosystem. The AWS Machine Learning Specialty case studies are 5 cases and about 2,751 words.
1Streaming Feature Freshness vs. Replay Cost
A fraud-detection team runs a Kinesis Data Stream with 8 shards receiving ~4,000 records/sec at peak. A Lambda consumer enriches each record and writes to DynamoDB, which a SageMaker real-time endpoint reads as a feature store at inference.
584 words, about 3 min2S3 Layout and Partitioning for a Training Set
A team stores 4 years of clickstream Parquet in S3 under s3://lake/events/year=/month=/day=/hour=/, about 120 GB/day, ~180 TB total. Analysts query with Athena and complain that a 7-day lookback scan costs far more than expected.
578 words, about 3 min3Class Imbalance and Threshold Selection Under a Cost Constraint
A team builds a binary classifier for equipment failure on 2.1 million sensor windows, of which 0.9% are failures. They train XGBoost with default settings and get ROC-AUC 0.94 but recall 0.31 at the default 0.5 threshold.
491 words, about 2 min4Endpoint Autoscaling and Deployment Safety
A recommendation model is served by a SageMaker real-time endpoint with 3 ml.c5.2xlarge instances. Traffic is diurnal: ~50 req/sec at night and ~900 req/sec during a 2-hour evening peak, with p99 latency target of 150 ms.
535 words, about 3 min5Retraining Trigger and Data Drift Diagnosis
A demand-forecasting model is retrained monthly on 3 years of history. Recently, forecast error (MAPE) rose from 11% to 19% over six weeks.
563 words, about 3 min