Time series evaluation metrics in ML Python - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is Mean Absolute Error (MAE) in time series evaluation?

MAE measures the average absolute difference between predicted and actual values. It shows how far predictions are from true values on average, using simple absolute differences.

beginner

Explain Mean Squared Error (MSE) and why it is used.

MSE calculates the average of squared differences between predicted and actual values. Squaring emphasizes larger errors, making MSE sensitive to big mistakes.

beginner

What does Root Mean Squared Error (RMSE) represent?

RMSE is the square root of MSE. It gives error in the same units as the data, making it easier to understand how far predictions are from actual values.

intermediate

Describe Mean Absolute Percentage Error (MAPE) and its limitation.

MAPE shows average absolute error as a percentage of actual values. It is easy to interpret but can be misleading if actual values are near zero, causing very high or undefined percentages.

intermediate

Why is R-squared (Coefficient of Determination) used in time series evaluation?

R-squared measures how well the model explains the variation in the data. A value close to 1 means predictions fit the data well, while values near 0 mean poor fit.

Which metric gives error in the same units as the original data?

A Mean Squared Error (MSE)

B Root Mean Squared Error (RMSE)

C Mean Absolute Error (MAE)

D Mean Absolute Percentage Error (MAPE)

RMSE is the square root of MSE, so it has the same units as the original data, making it easier to interpret.

Which metric can be misleading when actual values are close to zero?

A MAPE

B R-squared

C RMSE

D MAE

MAPE divides by actual values, so when actual values are near zero, it can produce very large or undefined percentages.

What does a high R-squared value indicate in time series evaluation?

A Overfitting

B Poor model fit

C High error

D Good model fit

A high R-squared means the model explains most of the variation in the data, indicating good fit.

Which metric penalizes larger errors more heavily?

A MAE

B MAPE

C MSE

D R-squared

MSE squares the errors, so larger errors have a bigger impact on the metric.

Which metric is best to use when you want an error measure easy to understand as a percentage?

A MAPE

B RMSE

C MAE

D MSE

MAPE expresses error as a percentage, making it easy to understand relative error size.

Describe the main differences between MAE, MSE, and RMSE for evaluating time series predictions.

Think about how each metric treats errors and their units.

Explain why MAPE can be problematic with certain time series data and when you might avoid using it.

Consider what happens when dividing by numbers close to zero.