You are an ML engineer at an ecommerce company and have been tasked with building a model that predicts how much inventory the logistics team should order each month. Which approach should you take?

Question

Options

• AUse a clustering algorithm to group popular items together. Give the list to the logistics team so
• BUse a regression model to predict how much additional inventory should be purchased each
• CUse a time series forecasting model to predict each item's monthly sales. Give the results to the
• DUse a classification model to classify inventory levels as UNDER_STOCKED, OVER_STOCKED,

• A
  6% (4)
• B
  1% (1)
• C
  88% (61)
• D
  4% (3)

Explanation

Inventory ordering is inherently a time-dependent problem driven by historical sales patterns, seasonality, and trends. A time series forecasting model is specifically designed to predict future values based on past temporal data, making it the ideal approach to predict monthly sales per item. Regression (B) ignores temporal structure, clustering (A) groups items but doesn't predict quantities, and classification (D) produces coarse categorical labels (UNDER/OVER_STOCKED) that are too imprecise for actionable ordering decisions.

No community discussion yet for this question.