MLS-C01 Question 144
Single answerA retail company wants to forecast the number of items it needs to stock in its warehouses for the next quarter. The dataset includes historical sales data, seasonal trends, and marketing campaign information. Which model should you choose to solve this problem?
- A
Linear Regression
- B
XGBoost Classifier
- C
ARIMA
- D
K-Means Clustering
Show answer and explanation
Correct answer: C
Explanation
ARIMA is the most appropriate model for this scenario because it is designed for time series forecasting. The problem involves predicting future stock levels based on historical data and trends, which aligns with the capabilities of ARIMA. Other models like Linear Regression and K-Means are not suitable for capturing temporal dependencies, and XGBoost Classifier is designed for classification tasks, not regression or forecasting.
- A. Incorrect.
Linear Regression is not ideal for time series forecasting as it does not account for temporal dependencies in the data.
- B. Incorrect.
XGBoost Classifier is a classification model and cannot be used for forecasting continuous numerical values like stock levels.
- C. Correct.
ARIMA (AutoRegressive Integrated Moving Average) is specifically designed for time series forecasting and can model temporal dependencies, making it suitable for this use case.
- D. Incorrect.
K-Means Clustering is used for unsupervised clustering and is not suitable for time series forecasting tasks.