
Ultimate access to all questions.
Your team is developing a machine learning solution on Google Cloud to classify support requests for a platform, aiming for full control over the model's code, serving, and deployment using TensorFlow. The project has tight deadlines and budget constraints, requiring an efficient approach that leverages existing resources and managed services without starting from scratch. Additionally, the solution must be scalable to handle increasing volumes of support requests and comply with data privacy regulations. Considering these requirements, what is the best approach to construct this classifier? (Choose two options if E is available)
A
Employ AutoML Natural Language to construct the support requests classifier, benefiting from its ease of use and quick deployment capabilities.
B
Utilize the Natural Language API to categorize support requests, taking advantage of its pre-trained models for immediate use.
C
Implement a pre-existing text classification model on AI Platform as-is to categorize support requests, saving development time but offering no customization.
D
Implement a pre-existing text classification model on AI Platform to execute transfer learning, customizing the model to better fit the specific requirements of the platform.
E
Combine the use of AI Platform for model customization with AutoML Natural Language for scenarios where quick deployment is critical, ensuring both flexibility and efficiency.