Question 7
A retail company is building a time series forecasting model to predict weekly sales. The dataset consists of 104 weeks of data. The analyst decides to split the data into a training set (80% of the data) and a test set (20% of the data). The analyst also observes that the sales data has a weekly seasonality.
Before fitting the model, the analyst applies the following preprocessing steps:
1. Seasonal differencing to remove the weekly seasonality. 2. First-order differencing to make the series stationary.
If the analyst uses a simple ARIMA (2, 1, 1) model (after preprocessing), how many total terms will the model include for AR, MA, and differencing?
2
3
4
5