Day 4 - GCP ML

 You are building an ML model to detect anomalies in real-time sensor data. You will use Pub/Sub to handle incoming requests. You want to store the results for analytics and visualization. How should you configure the pipeline? 

• 1 = Dataflow, 2 = AI Platform, 3 = BigQuery

• 1 = DataProc, 2 = AutoML, 3 = Cloud Bigtable

• 1 = BigQuery, 2 = AutoML, 3 = Cloud Functions

• 1 = BigQuery, 2 = AI Platform, 3 = Cloud Storage

Which of the GCP tool is serverless and uses SQL syntax

• Data Fusion

• BigQueryML

• Data Catalog

• Dataflow

How to use trained model for batch prediction stored in BiqQuery

• Export model to Bigquery ML

• Deploy model on Vertex AI

• Use dataflow to read data from bigquery

• Use Pub Sub

Where labels are not available, for example where customer segmentation is required, which of the following BigQuery supported models is useful?

• Time Series Forecasting

• K-Means Clustering

• Recommendation - Matrix Factorization

• Time Series Anomaly Detection

Which of the model isnt avaiable on BigQueryML?

• Forecasting

• Classification

• NLP

• Recommendation