DebiAI aims to facilitate the process of developing Machine Learning models, especially in the stage of training or evaluation data analysis and model performance comparaison.

In short, DebiAI provides data scientists with features to:

  • Identify biases and errors in your project data, whether it is training, test, contextual or target/ground truth data
  • Make a comparison of the performance of Machine Learning models according to their contextual results
  • Select and/or create sets of data graphically or using filtering features for further analysis or (re-)training purposes
  • Quickly create and share statistical visualisations of your project data in live

DebiAI has a Graphical User Interface with a complete data visualisation toolkit offering many statistical analysis tools:

The dashboard is higly customizable and can be used for big or small projects.

A python module is provided to insert directly from your Python workflow the data and model results that you want to analyse.


View Github