How confident is the system about the forecast accuracy?

In this section, the best explainable visualisations to check the predictions’ level of confidence are displayed. Specifically, this section serves as a valuable resource for evaluating the robustness of predictions and enhancing your overall comprehension of the predictive outcomes.

<span data-metadata=""><span data-metadata=""><span data-buffer="">Heatmap

Description

Example from XMANAI

A heatmap is a visual representation of data in the form of a colored matrix, where colors indicate numerical values in the matrix cells. Typically, more intense colors represent higher or lower values depending on the context. Heatmaps are used to highlight patterns and relationships in data, making it easier to understand trends. They are often employed to visualize the correlation between variables in a dataset or to represent the distribution of values in a matrix.

A 3D heatmap representation has been used in XMANAI to highlight the predicted measurement error on a spherical surface. The 3 axys (x, y, z) constitute the 3d space – expressed in mm – in which each error point is represented. The points are represented in a specific point of the space using a gradient color scale to identify the intensity of the error.