In practical machine learning problems, it is important to understand impact of features on models’ predictions. Such an understanding helps not only better explain the black-box machine learning models but also enables their effective applications in business environment. The general model explanation approaches make an untenable assumption that the model’s features are uncorrelated, which can lead to incorrect or unintelligible explanations.

Despite the advances of Machine Learning, the models are still being considered black-boxes that are difficult to diagnose and explain. The model performance diagnostic measures are critical to the assessment of the model’s relevance, accuracy and robustness. Good models’ performance is the primary enabler of their successful deployment in real-life applications. However, even if the models perform well, it is not known why the models predict the way they do, that is, which input variables are responsible for the models’ predictions.