MLS-C01 Exam - Question 69

Question

A large consumer goods manufacturer has the following products on sale:

* 34 different toothpaste variants

* 48 different toothbrush variants

* 43 different mouthwash variants

The entire sales history of all these products is available in Amazon S3. Currently, the company is using custom-built autoregressive integrated moving average

(ARIMA) models to forecast demand for these products. The company wants to predict the demand for a new product that will soon be launched.

Which solution should a Machine Learning Specialist apply?

Examice · Accepted Answer

To forecast demand for the new product, using the Amazon SageMaker DeepAR algorithm is the most suitable solution. DeepAR is a supervised learning algorithm designed specifically for time series forecasting using recurrent neural networks (RNN). It excels in scenarios where there are multiple related time series, such as the different variants of toothpaste, toothbrushes, and mouthwash. This algorithm can utilize the entire sales history available in Amazon S3 to generate accurate forecasts, even for new products. Classical models like ARIMA may not perform as well with the large amount of diverse time series data due to their limitations in handling scalability and complexity.

HaiHN · Answer

B
https://docs.aws.amazon.com/sagemaker/latest/dg/deepar.html
"...When your dataset contains hundreds of related time series, DeepAR outperforms the standard ARIMA and ETS methods. You can also use the trained model to generate forecasts for new time series that are similar to the ones it has been trained on."

Valcilio · Answer

DeepAr for new products forever!

hans1234 · Answer

It is B

AjoseO · Answer

The DeepAR algorithm is a powerful time series forecasting algorithm that is designed to handle multiple time series data and can handle irregularly spaced time series data and missing values, making it a good fit for this task.

Additionally, the large amount of sales history data available in Amazon S3 makes the use of a deep learning algorithm like DeepAR more appropriate.

ac427 · Answer

This is the same question as Topic 2 Q4

Shailendraa · Answer

B https://docs.aws.amazon.com/sagemaker/latest/dg/deepar.html

Mickey321 · Answer

Option B

loict · Answer

B - DeepAR is based on GluonTS, and can use multiple time series for learning

james2033 · Answer

'autoregressive integrated moving average (ARIMA)' <--> DeepAR. https://docs.aws.amazon.com/sagemaker/latest/dg/deepar.html

ninomfr64 · Answer

"You can also use the trained model to generate forecasts for new time series that are similar to the ones it has been trained on"
https://docs.aws.amazon.com/sagemaker/latest/dg/deepar.html

MLS-C01 Exam - Question 69

Discussion