The article presents a scenario involving the development of a machine learning (ML) model for predicting used car prices. The model uses data such as location, condition, model type, color, and engine/battery efficiency, updated nightly. The goal is to create a cost-effective retraining workflow using Google's Vertex AI platform.
Four options for configuring a retraining workflow are provided. These options differ in how they compare model performance (using training/evaluation losses or comparing to previous runs) and whether they incorporate model monitoring using training/serving skew thresholds.
The suggested solution is option D: Comparing performance to previous runs and deploying with model monitoring. This is more cost-effective because it avoids unnecessary redeployments unless model performance significantly degrades.
You are developing an ML model that predicts the cost of used automobiles based on data such as location, condition, model type, color, and engine/battery efficiency. The data is updated every night. Car dealerships will use the model to determine appropriate car prices. You created a Vertex AI pipeline that reads the data splits the data into training/evaluation/test sets performs feature engineering trains the model by using the training dataset and validates the model by using the evaluation dataset. You need to configure a retraining workflow that minimizes cost. What should you do?
If you often open multiple tabs and struggle to keep track of them, Tabs Reminder is the solution you need. Tabs Reminder lets you set reminders for tabs so you can close them and get notified about them later. Never lose track of important tabs again with Tabs Reminder!
Try our Chrome extension today!
Share this article with your
friends and colleagues.
Earn points from views and
referrals who sign up.
Learn more