Concession-stand review notes need a polarity tag on a few thousand lines. A week of GPU training would exceed the parks budget; an on-demand AI or foundation-model call would not. Which constraint should decide the model?
Select an answer to reveal the explanation.
Short Explanation
Think of polarity tags on a few thousand review lines, and a week of GPU training blowing the parks budget. Cost decides. Prefer a managed AI service or Bedrock on-demand over a long custom job.
Full Explanation
When cost is the stated constraint, pick the cheaper fitting option: a managed AI service or Bedrock on-demand rather than a long custom GPU job. Ignoring cost, Polly, and assuming K-Means is automatically cheapest miss that selection rule.