# How can I export Gradient Boosted Trees Learner in the PMML format? **URL:** \ **Category:** KNIME Analytics Platform\ **Created:** [July 6, 2022, 6:20am UTC](https://forum.knime.com/t/how-can-i-export-gradient-boosted-trees-learner-in-the-pmml-format/44814 "2022-07-06T06:20:11Z")\ **Posts on this page:** 1\ **Showing post:** 2
**Author:** ![mlauber71](https://forum-cdn.knime.com/user_avatar/forum.knime.com/mlauber71/32/73590_2.png) [@mlauber71](https://forum.knime.com/u/mlauber71)\ **Post date:** [July 6, 2022, 6:44am UTC](https://forum.knime.com/t/how-can-i-export-gradient-boosted-trees-learner-in-the-pmml-format/44814/2 "2022-07-06T06:44:10Z")
@somnathdas76 welcome to the KNIME forum. You could try and use these node > **[Gradient Boosted Trees to PMML](https://hub.knime.com/knime/extensions/org.knime.features.ensembles/latest/org.knime.base.node.mine.treeensemble2.node.gradientboosting.pmml.exporter.GBTPMMLExporterNodeFactory)** > > Writes a Gradient Boosted Trees model to PMML. Models learned on bit-, byte- or double-vector columns can be translated but the node will show a warning that t… > **[PMML Gradient Boosted Trees Predictor](https://hub.knime.com/knime/extensions/org.knime.features.ensembles/latest/org.knime.base.node.mine.treeensemble2.node.gradientboosting.predictor.pmml.GradientBoostingClassificationPMMLPredictorNodeFactory3)** > > Applies classification from a Gradient Boosted Trees model that is provided in PMML format. Note that it is currently not possible to load models that were lea… You can see examples of workflows at the bottom of the pages. If you want to use such a model in other environments H2O.ai and mojo format might be an option > [@KNIME ML to Python](https://forum.knime.com/t/knime-ml-to-python/44220/2): > > @BrBr two options would be to use H2O.ai models or PMML About pmml: > [@PMML Predictor: Add Class Probabilities](https://forum.knime.com/t/pmml-predictor-add-class-probabilities/6049/4): > > @arianiherrera not types of models support class probabilities with PMML (I am not aware of any changes since then): You could try and build a workflow with This does support probabilities. You might have to toy around to make it work. Currently there is no example workflow on the hub - which corresponds with my recollection that this is not that easy to set up. --- _[View the full topic](https://forum.knime.com/t/how-can-i-export-gradient-boosted-trees-learner-in-the-pmml-format/44814)._