AIF-C01 Question 11
Single answerA retail company wants to use a machine learning model to predict product demand based on historical sales data. They plan to process predictions for the entire dataset once daily to update their inventory projections. Which type of inferencing is most suitable for this use case?
- A
Batch inferencing
- B
Real-time inferencing
- C
Edge inferencing
- D
Online learning
Show answer and explanation
Correct answer: A
Explanation
The scenario describes a use case where predictions are made for the entire dataset on a daily basis, which aligns with batch inferencing. Batch inferencing processes predictions for a large dataset in a single operation, making it an efficient and cost-effective choice for non-real-time requirements like inventory updates.
- A. Correct.
Batch inferencing is the correct choice when predictions are generated for a large dataset at once, typically on a schedule, as described in the scenario.
- B. Incorrect.
Real-time inferencing is used when predictions are generated instantly in response to individual requests, which is not required in this scenario.
- C. Incorrect.
Edge inferencing refers to running models locally on edge devices, which is not relevant to the described use case involving inventory projections.
- D. Incorrect.
Online learning refers to a machine learning model that updates itself continuously as new data arrives, which is not applicable here since the scenario focuses on inferencing, not model training.