Due to a recent rise in popularity and technicality, machine learning models have become more like "black boxes": they've become harder to understand and interpret especially models such as neural networks and ensemble methods, etc.
In light of this, we need to develop tools and methods to gain stakeholders trust, remove biases, explain how our models work, how predictions are made and ensure our models perform consistently throughout their lifecycle.
In this video, you will learn about Machine Learning interpretability framework, explainX, which utilizes cutting edge technologies developed at explainX and leverages optimized versions of several third-party libraries.
We will explain a CatBoost Classifier model by using explainX. You can simply follow the code and explain your model behavior as well.
Create a Free account (explainX) https://explainx.ai/register