What features can affect the deviations from the enviseged plan?
In this section, the best explainable visualisations to highlight the features’ influence on deviation are displayed. Specifically, this section will show you how to suggest which variables carry more relevance in the model’s planning predictions.
<span data-metadata=""><span data-buffer="">Decision Tree
Description
Example from XMANAI
A decision tree is a tree-like model that breaks down a complex decision-making process into a series of simpler decisions. The tree structure consists of nodes representing decisions or test points, branches representing possible outcomes, and leaves representing the final decision or classification. They are particularly effective for modeling decision processes with multiple possible outcomes and are valued for their interpretability, as they provide a transparent representation of decision logic.
A decision tree global surrogate has been used to offer a more transparent representation of
the decision-making process for the models used to predict point measurement error for a spherical surface. The decision-tree offer an intuitive
understanding of the model’s operation, making clear how the lowest measurement error have been predicted.
