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

Exercise

Identifying model drift

Now you'll plot the model scores over time to visualize when drift occurs. By adding the threshold line and RMSE rolling windows, you can see how the trailing error lines indicate performance degradation.

The fc_log dataset with calculated moving averages, rmse_threshold, and Plotly as go have been pre-loaded for you.

Instructions 1/2

undefined XP
    1
    2
  • Add rmse, rmse_ma_7, and rmse_ma_14 plots on code lines 4, 10, and 15, respectively.
  • Set the x-axis title as "Forecast Date" and the y-axis as "RMSE".