AWS Certified Machine Learning – Specialty — Question 225
A retail company wants to use Amazon Forecast to predict daily stock levels of inventory. The cost of running out of items in stock is much higher for the company than the cost of having excess inventory. The company has millions of data samples for multiple years for thousands of items. The company’s purchasing department needs to predict demand for 30-day cycles for each item to ensure that restocking occurs.
A machine learning (ML) specialist wants to use item-related features such as "category," "brand," and "safety stock count." The ML specialist also wants to use a binary time series feature that has "promotion applied?" as its name. Future promotion information is available only for the next 5 days.
The ML specialist must choose an algorithm and an evaluation metric for a solution to produce prediction results that will maximize company profit.
Which solution will meet these requirements?
Answer options
- A. Train a model by using the Autoregressive Integrated Moving Average (ARIMA) algorithm. Evaluate the model by using the Weighted Quantile Loss (wQL) metric at 0.75 (P75).
- B. Train a model by using the Autoregressive Integrated Moving Average (ARIMA) algorithm. Evaluate the model by using the Weighted Absolute Percentage Error (WAPE) metric.
- C. Train a model by using the Convolutional Neural Network - Quantile Regression (CNN-QR) algorithm. Evaluate the model by using the Weighted Quantile Loss (wQL) metric at 0.75 (P75).
- D. Train a model by using the Convolutional Neural Network - Quantile Regression (CNN-QR) algorithm. Evaluate the model by using the Weighted Absolute Percentage Error (WAPE) metric.
Correct answer: C
Explanation
The correct answer is C because the Convolutional Neural Network - Quantile Regression (CNN-QR) algorithm is well-suited for making predictions that can optimize profit in scenarios with uncertain demand. The Weighted Quantile Loss (wQL) metric at 0.75 (P75) is appropriate as it focuses on the upper tail of the distribution, which is crucial for avoiding stockouts. Options A and B utilize ARIMA, which may not capture the complexities of the data effectively, while option D fails to use the optimal evaluation metric for profit maximization.