Databricks Machine Learning Associate case studies
Databricks Machine Learning Associate · Put your knowledge to work in context.
The Databricks Certified Machine Learning Associate is a proctored certification that assesses an individual's ability to use Databricks to perform basic machine learning tasks. Per Databricks, the exam tests understanding of the platform and its machine learning capabilities - including AutoML, Unity Catalog, and select features of MLflow - as well as data exploration, feature engineering, and model building through training, tuning, evaluation and selection, plus model deployment. It is aimed at practitioners with roughly six or more months of hands-on experience performing the tasks outlined in the exam guide; there are no formal prerequisites, though related training is highly recommended. All machine learning code on the exam is Python, while data manipulation code in non-ML workflow contexts may be provided in SQL. The Databricks Machine Learning Associate case studies are 5 cases and about 2,070 words.
1Hyperparameter Sweep That Got Slower With More Parallelism
A team is tuning an XGBoost churn model on a 400M-row Delta table (~60 GB after feature expansion). The cluster has 8 workers, each 16 cores/64 GB, and a 32-core/128 GB driver.
425 words, about 2 min2Offline AUC 0.89, Online AUC 0.72
A churn model uses a 2B-row event table and a daily feature table ml.churn features . Training data is built with a hand-written AS OF join on event date ; batch scoring uses a separate SQL query that joins each customer to the current feature row.
423 words, about 2 min3Cold Starts on a Scale-to-Zero Fraud Endpoint
A fraud-scoring scikit-learn model is deployed to a Databricks Model Serving endpoint. Peak traffic is 20 requests/second; the business requires p95 < 200 ms.
428 words, about 2 min4Service Principal Cannot Create an Endpoint From a Unity Catalog Model
Unity Catalog is enabled. Models are registered as prod.ml.churn .
409 words, about 2 min5Auto-Promoting the Latest Model Broke Retention Offers
A nightly Databricks job trains a churn model, registers it as main.ml.churn , and a second task calls the serving API to point the endpoint at the newest version. There is no validation gate.
385 words, about 2 min