Microsoft Fabric Analytics Engineer Associate DP-600
Comments
Loading comments...
Ultimate access to all questions.
As a Microsoft Fabric Analytics Engineer Associate working on a data analytics project for a financial services company, your goal is to detect and prevent fraudulent transactions. The company has provided you with a large dataset containing transaction records, including transaction amounts, dates, and customer information. Given the company's requirements for high accuracy, scalability, and compliance with financial regulations, which of the following techniques would be the MOST comprehensive approach to analyze this dataset and identify potential fraudulent transactions? Choose the best option.
A
Implementing only anomaly detection algorithms to identify transactions that deviate from normal patterns, focusing solely on unusual transaction amounts.
B
Applying supervised learning algorithms to classify transactions as fraudulent or legitimate based on historical data, without considering the relationships between different transaction features.
C
Utilizing association rule mining to uncover relationships between transaction features and fraudulent activity, ignoring the classification of transactions based on historical data.
D
Combining anomaly detection algorithms, supervised learning algorithms, and association rule mining to provide a holistic view of potential fraudulent transactions by identifying deviations, classifying based on history, and understanding feature relationships.