Q: 4
A company has petabytes of unlabeled customer data to use for an advertisement campaign. The
company wants to classify its customers into tiers to advertise and promote the company's products.
Which methodology should the company use to meet these requirements?
Options
Discussion
Probably B, since the data's unlabeled. A is tempting but that's a classic trap if you skim the question.
Definitely B here. Since they're dealing with petabytes of unlabeled data, clustering with unsupervised learning is what AWS tests on for this type of customer segmentation. Seen similar in exam reports, but happy to hear if someone disagrees.
B I remember a similar scenario from labs where unsupervised learning was the right call for unlabeled data.
B makes sense since the question says they've got only unlabeled data. Unsupervised learning like clustering is meant for grouping similar items without labels, so that's what you'd use here. Pretty sure that's AWS's typical way to handle this, agree?
I don't think it's B here, I'd actually pick A. The company needs customer tiers, so you’d need to provide those labels and train the model that way. Looks like a trap since classification usually means supervised learning.
B , the question makes it pretty clear it's all unlabeled data so unsupervised fits best for that clustering/classifying into tiers. Not 100 percent but that's how I'd approach it, let me know if you disagree.
A , since a lot of customer classification feels like it needs prior labels. B looks like a trap.
Option B unsupervised learning. This shows up in AWS official guide examples when dealing with huge unlabeled datasets like this.
B tbh
A is out, B makes sense if the customer data is really unlabeled. Classic clustering scenario.
Be respectful. No spam.
