Exam AI-100 All Questions

View all questions & answers for the AI-100 exam

Exam AI-100 topic 2 question 1 discussion

Actual exam question from Microsoft's AI-100

Question #: 1
Topic #: 2

HOTSPOT -
You are designing a solution that will analyze bank transactions in real time. The transactions will be evaluated by using an algorithm and classified into one of five groups. The transaction data will be enriched with information taken from Azure SQL Database before the transactions are sent to the classification process. The enrichment process will require custom code. Data from different banks will require different stored procedures.
You need to develop a pipeline for the solution.
Which components should you use for data ingestion and data preparation? To answer, select the appropriate options in the answer area.
NOTE: Each correct selection is worth one point.
Hot Area:

Show Suggested Answer

Suggested Answer:

References:
https://docs.microsoft.com/bs-latn-ba/azure/architecture/example-scenario/data/fraud-detection

by RishiAI at Sept. 25, 2019, 12:27 a.m.

Comments

Submit Cancel

Nova077

Highly Voted 4 years, 9 months ago

we are not doing Analytics on a streaming data. We will do data enrichment by using queries ( stored procedures). Hence my vote is for Azure Functions.

upvoted 8 times

Ndubai

4 years, 8 months ago

https://docs.microsoft.com/en-us/azure/stream-analytics/stream-analytics-edge-csharp-udf-methods

upvoted 1 times

...

giusecozza

Highly Voted 5 years, 1 month ago

Azure Functions could be an option here, maily for two reasons: 1. data preparation require custom code 2. "An Azure Function integrated with SQL Database provides multiple benefits: ... Doing the bulk of data preparation using SQL Database in-memory processing and native stored procedures was very fast" https://azure.microsoft.com/it-it/blog/considering-azure-functions-for-a-serverless-data-streaming-scenario/

upvoted 5 times

carloshvp

5 years ago

Stream Analytics is designed for real-time and can run custom code (Stream Analytics Query Language, which is T-SQL like). https://docs.microsoft.com/en-us/stream-analytics-query/stream-analytics-query-language-reference

upvoted 5 times

carloshvp

5 years ago

Therefore Stream Analytics is correct

upvoted 1 times

giusecozza

5 years ago

Functions are well suited for real-time processing too. Moreover, the question is asking for a component for "data preparation", which is a good use case for Functions. Finally, I'm not sure Stream Analytics supports calls for Stored Procedures. Some users were complaining about this on the blogs below: https://feedback.azure.com/forums/270577-stream-analytics/suggestions/38438074-support-sql-db-stored-procedures-as-asa-output https://stackoverflow.com/questions/44026676/how-can-i-set-stream-analytics-output-as-stored-procedure

upvoted 4 times

Arinze

4 years, 10 months ago

Because Azure Event Hubs can be an input to Stream Analytics but not to Azure Functions, I would say Stream Analytics is the answer not Azure Functions

upvoted 3 times

Cornholioz

4 years, 4 months ago

Sure it can: https://docs.microsoft.com/en-us/azure/azure-functions/functions-reliable-event-processing https://docs.microsoft.com/en-us/azure/azure-functions/functions-bindings-event-hubs-trigger?tabs=csharp

upvoted 2 times

...

rveney

Most Recent 1 year, 12 months ago

components to be used for data ingestion and data preparation are: Data Ingestion: Azure Event Hubs Data Preparation: Azure Functions

upvoted 1 times

...

123aditya

3 years, 11 months ago

Analytics is correct as it will be used to "process the data" https://docs.microsoft.com/en-in/azure/stream-analytics/stream-analytics-with-azure-functions

upvoted 1 times

...

damirbek369

3 years, 12 months ago

According to this quote "Azure Stream Analytics is an event-processing engine that can analyze high volumes of data streaming from devices and other data sources. It also supports extracting information from data streams to identify patterns and relationships. These patterns can trigger other downstream actions. In this scenario, Stream Analytics transforms the input stream from Event Hubs to identify fraudulent calls." IMO the second answer is Stream Analytics. https://docs.microsoft.com/bs-latn-ba/azure/architecture/example-scenario/data/fraud-detection

upvoted 1 times

...

AlfuryDB

4 years, 3 months ago

This links explains it all: https://docs.microsoft.com/en-us/azure/azure-functions/functions-bindings-event-hubs-trigger?tabs=csharp you can use a function and the trigger can come from event hubs. Therefore, Event hubs and azure functions 100% sure

upvoted 3 times

...

vilas94

4 years, 8 months ago

The question says the enrichment process will require custom code, The only option for this is azure Functions. Azure stream Analytics can also has custom code But this option has off 09/10/2020 is in Preview https://docs.microsoft.com/en-us/azure/stream-analytics/stream-analytics-edge-csharp-udf-methods

upvoted 4 times

...

CeliaZhou

4 years, 8 months ago

According to this article, the solution seems to be: Event hub+Azure Functions https://azure.microsoft.com/hu-hu/blog/considering-azure-functions-for-a-serverless-data-streaming-scenario/

upvoted 5 times

...

abbam

5 years, 1 month ago

My thoughts regarding the 2nd answer: Agree azure Stream Analytics is good candidate for real-time analytics and complex event-processing and designed for high volumes of fast streaming data but the question here is about preparing the data and also remember the data enrichment is done at the SQL DB level and there is already an algorithm that does the classification. An azure function could act as an orchestrator, not doing any heavy lifting except loading data payload to azure SQL DB, the stored procedures computes/calculates the new features.

upvoted 4 times

adarshsahoo

3 years, 7 months ago

You are representing your thoughts, but why? Is this Roadies or Splitsvilla? This Azure -100.... Behave properly....nahale bhara khaibu

upvoted 1 times

...

RishiAI

5 years, 8 months ago

In the first part-> The answer should be Azure IOT Hub...Why Not Event Hub ? Because the IOT Hub contains and Event Hub and hence essentially is an additional features. More important thing is that Event Hub can only receive message,where as IOT hub can send messages to individual devices.

upvoted 1 times

T0p1cs

5 years, 8 months ago

There is no requirement to write back to the devices nor anything around device management. Therefore I would go with Event Hub

upvoted 26 times

carloshvp

5 years ago

Event Hub is correct

upvoted 3 times

...