Azure DP-100 case studies

Azure DP-100 · Put your knowledge to work in context.

Exam DP-100 leads to the Microsoft Certified: Azure Data Scientist Associate credential, an intermediate-level certification for data scientists who apply data science and machine learning to run workloads on Azure. Microsoft's certification page carries a warning that the certification and its renewal assessment are retired, so candidates should check Microsoft Learn for current credential options before scheduling. The Azure DP-100 case studies are 5 cases and about 3,880 words.

Lineage and network isolation for a 4 TB/day telemetry pipeline

Contoso runs a single Azure Machine Learning workspace in West Europe. Raw telemetry lands in ADLS Gen2 as roughly 4 TB of hourly Parquet partitions per day.

755 words, about 4 min 2

Fraud model with 0.8% positives, a 500-alert budget, and a new payment provider

A payments team trains a fraud classifier on 12 million transactions from the past two years; 0.8% are fraud. The current model reports ROC AUC 0.94 and accuracy 99.2%, and it was deployed at a 0.5 threshold.

719 words, about 4 min 3

2 million nightly scores and a 150 ms storefront API from one model

A retail pricing model must score 2 million SKU/store combinations nightly from a full refresh, and also answer about 40 price-check requests per second at peak for a storefront API with p99 under 150 ms. The model is a 900 MB gradient-boosted ensemble registered in the workspace.

840 words, about 4 min 4

Cutting a 50-hour epoch to a 6-hour wall clock on a shared 8-node quota

A team fine-tunes a vision transformer on 1.2 million images. On a single ND40rs v2 node (8x V100) one epoch takes 5 hours, and the training budget is 10 epochs.

764 words, about 4 min 5

RAG assistant at 6.8 s p95 and $9,200/month: fix retrieval or fine-tune?

A support assistant answers product questions with a RAG pipeline: a 3,000-token system prompt, 12 retrieved chunks of about 500 tokens each, and a GPT-4o deployment that returns four sentences. Volume is 400,000 requests per month.

802 words, about 4 min