Data Science - Time Series Forecasting with Facebook Prophet in Python - Prophet in Code: Cross-Validation

The video tutorial covers the process of cross validation in profit, starting with importing and calling the cross validation function. It explains the output data frame and introduces performance metrics like MSE and RMSE. The tutorial demonstrates plotting cross validation metrics and compares different models, highlighting the impact of removing zero sales days. The conclusion emphasizes the importance of model adjustments for better performance.

What is the purpose of the cross validation function in Prophet?

• To import data into Prophet

• To visualize the model's predictions

• To validate the model's performance over a specified horizon

• To train a new model

Which of the following is NOT a component of the data frame returned by the cross validation function?

• Initial

• Cutoff

• Y hat

• DS

What does the performance metrics function return?

• A summary of the training data

• A plot of the model's predictions

• A list of model parameters

• A data frame with various error metrics

Why was MAPE skipped in the performance metrics?

• The horizon was too short

• The model was not trained properly

• The target values were close to zero

• The target values were too high

What pattern is observed when plotting the cross validation metric for the second model?

• A constant value

• A random scatter

• A cyclical pattern

• A linear increase

Which model had the best performance in terms of mean S MAPE?

• The model with US holidays

• The model with zero sales days removed

• The model with external regressors

• The initial model with all data

What was the impact of adding US holidays to the model?

• It had no effect

• It slightly worsened the model

• It caused the model to fail

• It significantly improved the model