ExamTopics Logo
Mail Us[email protected]
Menu
Amazon Discussions
exam questions

Exam AWS Certified Data Analytics - Specialty All Questions

View all questions & answers for the AWS Certified Data Analytics - Specialty exam
Go to Exam

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

Exam question from Amazon's AWS Certified Data Analytics - Specialty
Question #: 84
Topic #: 1
[All AWS Certified Data Analytics - Specialty Questions]

A telecommunications company is looking for an anomaly-detection solution to identify fraudulent calls. The company currently uses Amazon Kinesis to stream voice call records in a JSON format from its on-premises database to Amazon S3. The existing dataset contains voice call records with 200 columns. To detect fraudulent calls, the solution would need to look at 5 of these columns only.
The company is interested in a cost-effective solution using AWS that requires minimal effort and experience in anomaly-detection algorithms.
Which solution meets these requirements?

  • A. Use an AWS Glue job to transform the data from JSON to Apache Parquet. Use AWS Glue crawlers to discover the schema and build the AWS Glue Data Catalog. Use Amazon Athena to create a table with a subset of columns. Use Amazon QuickSight to visualize the data and then use Amazon QuickSight machine learning-powered anomaly detection.
  • B. Use Kinesis Data Firehose to detect anomalies on a data stream from Kinesis by running SQL queries, which compute an anomaly score for all calls and store the output in Amazon RDS. Use Amazon Athena to build a dataset and Amazon QuickSight to visualize the results.
  • C. Use an AWS Glue job to transform the data from JSON to Apache Parquet. Use AWS Glue crawlers to discover the schema and build the AWS Glue Data Catalog. Use Amazon SageMaker to build an anomaly detection model that can detect fraudulent calls by ingesting data from Amazon S3.
  • D. Use Kinesis Data Analytics to detect anomalies on a data stream from Kinesis by running SQL queries, which compute an anomaly score for all calls. Connect Amazon QuickSight to Kinesis Data Analytics to visualize the anomaly scores.
Show Suggested Answer Hide Answer
Suggested Answer: A 🗳️
by VikG12 at May 3, 2021, 5:41 p.m.
Disclaimers:
  • - ExamTopics website is not related to, affiliated with, endorsed or authorized by Amazon.
  • - Trademarks, certification & product names are used for reference only and belong to Amazon.

Comments

Chosen Answer:
This is a voting comment (?). It is better to Upvote an existing comment if you don't have anything to add.
Switch to a voting comment New
Submit Cancel
Heer
Highly Voted 3 years, 8 months ago
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.
upvoted 29 times
...
cloudlearnerhere
Highly Voted 2 years, 7 months ago
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.
upvoted 7 times
...
Debi_mishra
Most Recent 2 years ago
A is the best among worst but still wrong. Why the need of creating Athena table again on top of Catalog? Its already Parquet.
upvoted 1 times
...
pk349
2 years, 1 month ago
A: I passed the test
upvoted 1 times
...
James_Mao
2 years, 9 months ago
C : https://aws.amazon.com/blogs/big-data/detecting-anomalous-values-by-invoking-the-amazon-athena-machine-learning-inference-function/
upvoted 1 times
...
rocky48
2 years, 10 months ago
Selected Answer: A
Answer - A
upvoted 1 times
...
jrheen
3 years, 1 month ago
Answer - A
upvoted 1 times
...
astalavista1
3 years, 2 months ago
Selected Answer: A
ML-powered anomaly detection.
upvoted 3 times
...
yogen
3 years, 5 months ago
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/
upvoted 3 times
...
Thiya
3 years, 6 months ago
Answer is A Option D also wrong as QuickSight cannot connect to any of Kinesis services.
upvoted 4 times
...
aws2019
3 years, 6 months ago
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/
upvoted 1 times
...
goutes
3 years, 7 months ago
A because : Quicksight Machine Learning Insights can use random_cut_forest .
upvoted 1 times
...
ThomasKalva
3 years, 7 months ago
Option A based on https://docs.aws.amazon.com/quicksight/latest/user/anomaly-detection-function.html
upvoted 1 times
...
Donell
3 years, 7 months ago
Answer is A.
upvoted 1 times
...
Huy
3 years, 7 months ago
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.
upvoted 1 times
...
KingD
3 years, 7 months ago
Best answer is A. kindly refer to documentation below for confirmation thanks. https://aws.amazon.com/quicksight/features-ml/
upvoted 2 times
...
ariane_tateishi
3 years, 8 months ago
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
upvoted 3 times
asg76
3 years, 8 months ago
but what about "Connect Amazon QuickSight to Kinesis Data Analytics to visualize the anomaly scores" ? Not sure if you can connect Quicksight to Data Analytics like this. So A seems to be a more logical answer.
upvoted 2 times
...
shato944
3 years, 7 months ago
Kinesis Data Analytics can write only to three services: - Firehose - Kinesis data streams - lambda See https://docs.aws.amazon.com/kinesisanalytics/latest/dev/how-it-works-output.html There is no way to write to QuickSight
upvoted 3 times
tobsam
3 years, 6 months ago
Answer is A. from d above quicksight docs: External destination – You can persist data to a Kinesis data stream, a Kinesis Data Firehose delivery stream, or a Lambda function.
upvoted 1 times
...
...
...
Load full discussion...
Community vote distribution
A (35%)
C (25%)
B (20%)
Other
Most Voted
A voting comment increases the vote count for the chosen answer by one.

Upvoting a comment with a selected answer will also increase the vote count towards that answer by one. So if you see a comment that you already agree with, you can upvote it instead of posting a new comment.

SaveCancel