MLS-C01 · Question #166
A company offers an online shopping service to its customers. The company wants to enhance the site's security by requesting additional information when customers access the site from locations that…
The correct answer is B. Use Amazon SageMaker to train a model using the IP Insights algorithm. Amazon SageMaker's IP Insights algorithm is specifically designed to learn the association patterns between entities (such as user login names) and IPv4 addresses. It builds an embedding that captures normal IP usage patterns per user and can score new (user, IP) pairs by how…
Question
A company offers an online shopping service to its customers. The company wants to enhance the site's security by requesting additional information when customers access the site from locations that are different from their normal location. The company wants to update the process to call a machine learning (ML) model to determine when additional information should be requested. The company has several terabytes of data from its existing ecommerce web servers containing the source IP addresses for each request made to the web server. For authenticated requests, the records also contain the login name of the requesting user. Which approach should an ML specialist take to implement the new security feature in the web application?
Options
- AUse Amazon SageMaker Ground Truth to label each record as either a successful or failed
- BUse Amazon SageMaker to train a model using the IP Insights algorithm.
- CUse Amazon SageMaker Ground Truth to label each record as either a successful or failed
- DUse Amazon SageMaker to train a model using the Object2Vec algorithm.
How the community answered
(49 responses)- A4% (2)
- B71% (35)
- C8% (4)
- D16% (8)
Explanation
Amazon SageMaker's IP Insights algorithm is specifically designed to learn the association patterns between entities (such as user login names) and IPv4 addresses. It builds an embedding that captures normal IP usage patterns per user and can score new (user, IP) pairs by how unusual they are - exactly what is needed to flag logins from unexpected locations. The existing web server logs containing source IPs and login names are the ideal training input for IP Insights. SageMaker Ground Truth (options A and C) is a data labeling service; labeling billions of IP records as 'successful/failed' is not practical and misframes the problem as supervised classification when anomaly detection is the right approach. Object2Vec (option D) is a general-purpose embedding algorithm not optimized for IP-entity relationship modeling.
Topics
Community Discussion
No community discussion yet for this question.