Exam AWS Certified Data Analytics - Specialty topic 1 question 84 discussion

OPTION A: Amazon QuickSight uses proven Amazon technology to continuously run ML-powered anomaly detection across millions of metrics to discover hidden trends and outliers in your data. This anomaly detection enables you to get deep insights that are often buried in the aggregates and not scalable with manual analysis.

Correct answer is A as only limited columns are required it would be best to convert the data in columnar format and expose it through Athena to QuickSight for anomaly detection. Using parquet with Athena helps provide a cost-effective solution using QuickSight requires minimal effort and experience in anomaly-detection algorithms. Link : https://docs.aws.amazon.com/quicksight/latest/user/anomaly-detection-function.html Option B is wrong as Kinesis Data Firehose does not provide analytic functions and cannot be used for anamoly detection Option C is wrong as using SageMaker would require more effort. Option D is wrong as Kinesis Data Analytics does not integrate with QuickSight directly.

A is the best among worst but still wrong. Why the need of creating Athena table again on top of Catalog? Its already Parquet.

A: I passed the test

C : https://aws.amazon.com/blogs/big-data/detecting-anomalous-values-by-invoking-the-amazon-athena-machine-learning-inference-function/

Answer - A

Answer - A

ML-powered anomaly detection.

The question is based on below blog and answer is A: https://aws.amazon.com/blogs/big-data/detect-fraudulent-calls-using-amazon-quicksight-ml-insights/

Answer is A Option D also wrong as QuickSight cannot connect to any of Kinesis services.

You can use D also but less effort = Option A (Quicksight) https://aws.amazon.com/blogs/big-data/detect-fraudulent-calls-using-amazon-quicksight-ml-insights/

A because : Quicksight Machine Learning Insights can use random_cut_forest .

Option A based on https://docs.aws.amazon.com/quicksight/latest/user/anomaly-detection-function.html

Answer is A.

A is correct. B wrong. Kinesis Data Firehose has no analytic function D wrong. SQL is not for anomaly detection and can't output to Quicksight C works but more effort.

Best answer is A. kindly refer to documentation below for confirmation thanks. https://aws.amazon.com/quicksight/features-ml/

D should be the right answer, considering that the requirement is develop a cost-effective solution using AWS that requires minimal effort and experience in anomaly-detection algorithms. With the option A we need the glue, athena and quicksight. With option D we only need stream analytics (using SQL sintax, very easy) and the quicksight. https://docs.aws.amazon.com/kinesisanalytics/latest/dev/app-anomaly-detection.html