Google Professional Machine Learning Engineer
Get started today
Ultimate access to all questions.
Ultimate access to all questions.
You are a data scientist working for a large retailer, and your current task is to build a predictive model to determine customer churn. The company has provided you with a dataset that includes historical customer data such as demographics, purchase history, and website activity. You plan to build the model using BigQuery ML. After building the model, you need to thoroughly evaluate its performance to ensure it meets business requirements for accuracy and reliability. What should you do?
Explanation:
The correct answer is B. The task is to predict customer churn, which is a binary classification problem (whether a customer will churn or not). Logistic regression is suitable for binary classification, making it the appropriate model. Vertex AI Model Registry allows for comprehensive model management and evaluation. It provides extensive evaluation metrics such as accuracy, ROC-AUC, precision, and recall, which are crucial for assessing the performance of churn prediction models. Thus, creating a logistic regression model in BigQuery ML and evaluating it in Vertex AI is the best approach.