Time-Series Model Evaluation Insights

Hard Time-series Analysis Model Evaluation

In an empirical study analyzing the monthly sales data of a retail company, a time-series model was fitted to capture the sales trend and seasonality. The model evaluation included metrics such as Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and R-squared. After achieving reasonable fit indicators, the model was further tested on a holdout sample of data to ensure its predictive efficacy.

Consider the following results from the model evaluation:

MAPE = 5%
RMSE = 10,000 units
R-squared = 0.85

Which of the following statements about the evaluation of this model is most accurate?

The model has a high predictive power as indicated by the R-squared value, but caution should be used given the high RMSE.

Although MAPE indicates excellent forecasting accuracy, RMSE suggests that the model may struggle with outlier predictions.

The MAPE value is low indicating that the model has high accuracy; however, R-squared suggests the model does not explain much of the variability.

Hint

Submitted13.6K

Correct11.8K

% Correct87%