New Core Feature: Add Time-Series Cross Validation

h2oai / h2o-3

H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.

Apache License 2.0

6.86k stars 1.99k forks source link

If you are looking forward to use H2O-3's Machine Learning Algorithms for Time Series Forecasting, H2O-3 does not offer an easy way to set a Time Series Cross-Validation scheme that prevents look-ahead.

We could of course simply use a time-aware "validation_frame", but using a Time Series aware cross validation will capture better seasonality.

Here are 2 articles which explain in detail the proposed Time Series Cross-Validation Scheme:

[https://robjhyndman.com/hyndsight/tscv/|https://robjhyndman.com/hyndsight/tscv/]

[https://towardsdatascience.com/time-series-nested-cross-validation-76adba623eb9|https://towardsdatascience.com/time-series-nested-cross-validation-76adba623eb9]

!cv1-1.png|width=200,height=183!

!fXZ6k.png|width=200,height=183!

h2oai / h2o-3

New Core Feature: Add Time-Series Cross Validation #8402