
Ultimate access to all questions.
You are tasked with developing a machine learning solution for a retail company that wants to predict customer churn based on historical transaction data stored in BigQuery. The solution must support exploratory data analysis, feature selection, model building, training, hyperparameter tuning, and serving, all without requiring manual coding. The company emphasizes the importance of scalability, cost-efficiency, and the ability to repeat the classification process across multiple datasets with minimal setup. Given these requirements, which of the following approaches is the most efficient? Choose the best option.
A
Utilize AI Platform Notebooks with custom Python scripts leveraging the pandas library for data manipulation and scikit-learn for model training, ensuring full control over the workflow.
B
Implement AutoML Tables to automate the entire machine learning workflow, from data preprocessing to model deployment, without writing any code.
C
Deploy a custom TensorFlow model on AI Platform, using AI Platform's hyperparameter tuning service to optimize the model performance.
D
Create a logistic regression model directly in BigQuery using BigQuery ML, enabling SQL-based model training and prediction.
E
Combine the use of AutoML Tables for initial model exploration and BigQuery ML for scalable model training and serving, to leverage the strengths of both services.