Skip to content

v3.9.0: Time-series validation feature

Compare
Choose a tag to compare
@laresbernardo laresbernardo released this 15 Dec 15:16
· 364 commits to main since this release
eabd4c8
  • Feat: new time series validation via time-series train/val/test dynamic splits and Adjusted R2 and NRMSE metrics reported for each group feature #545. We are adding an additional train_size hyperparameter to pick the size of the training size, which by default will iterate in the range of 0.5-0.8. Given it's a hyperparameter, you can change the range or fix the value manually. Turn on/off this feature using the ts_validation new parameter on robyn_run(); default is set to FALSE for now. This is an important step for the forecasting coming function.
  • Feat: new ts_validation() function to plot time-series validation and convergence results. Generated and exported by default when ts_validation = TRUE, and when export = TRUE, creating ts_validation_plot.png file.
  • Fix: updated Adjusted R2 calculation (get_rsq()) for time-series validation using same denominator.
  • Fix: results are not sorted by lowest errors now to keep iteration results actual order.
  • Feat: added prophet monthly component to enrich decomposition results #525
  • Fix: correct solID (not "1_1_1") for fixed hyperparameters recreated models.
  • Recode: reduced the size of xDecompVec on OutputCollect by keeping pareto-front models only.
  • Docs: changed standard inputs on demo.R file for modeling window to include more data (3 years by default).

New Contributors

Full Changelog: v3.8.2...v3.9.0