1. Learn
    2. /
  2. Courses
    3. /
  3. Designing Forecasting Pipelines for Production
Connected

Exercise

Training models with backtesting

Building on the previous exercises, you'll now evaluate your models using backtesting. You'll define 4 partitions, each with a 12-hour shift and a 72-hour testing window, and execute the process with the cross_validation() method.

The ts DataFrame and initialized MLForecast object (mlf) are preloaded, so you can focus on setting up and running the backtesting. Let's get started!

Instructions 1/2

undefined XP
    1
    2
  • Import the PredictionIntervals class required for interval calibration and set the parameters - forecast horizon to 72 and step size for cross-validation to 12.
  • Initialize the PredictionIntervals() object using the specified parameters.