Designing and Implementing an Azure AI Solution (legacy) — Question 11

You have an SAP production landscape.
You plan to use Azure Machine Learning to develop a fraud detection API. The API will identify potentially fraudulent transactions in the SAP production landscape in near real time.
You need to recommend a workflow for the API.
What should you recommend?

Answer options

• A. an Azure Data Factory pipeline that uses an SAP table connector and a Machine Learning Execute Pipeline activity
• B. a Microsoft Excel workbook that imports SAP transactions and uses the Excel add-in for web services to score the transactions
• C. an Azure logic app triggered by an SAP message that calls the API and sends an email based on the results
• D. a scheduled Jupyter Notebook in Azure Databricks that connects to SAP HANA

Correct answer: A

Explanation

The correct answer is A because an Azure Data Factory pipeline is designed to integrate data from SAP and facilitate the execution of machine learning models in a streamlined manner. The other options do not provide the same level of efficiency or real-time capabilities; for instance, using Excel (option B) is not practical for real-time processing, while an Azure logic app (option C) may introduce delays and a Jupyter Notebook (option D) lacks the automated pipeline features necessary for continuous fraud detection.