
Ultimate access to all questions.
As an ML engineer at a leading grocery retailer, you are tasked with developing an inventory prediction model to optimize stock levels across multiple stores. The model must incorporate various features such as region, location, historical sales data, seasonal trends, and promotional events to forecast inventory needs accurately. It should also dynamically adapt to daily updates in inventory data to ensure predictions remain relevant. Given the complexity of the data and the need for the model to learn from sequential data over time, which of the following algorithms is most suitable for this task? (Choose one correct option)
A
Classification algorithms, as they can categorize inventory levels into predefined classes based on input features.
B
Recurrent Neural Networks (RNN), due to their ability to process sequential data and learn from temporal patterns, making them ideal for time-series forecasting.
C
Convolutional Neural Networks (CNN), which are best suited for image recognition tasks and spatial data analysis.
D
Reinforcement Learning, as it can optimize inventory levels through trial and error based on reward feedback.