8 pitfalls to avoid while using Machine Learning Interpretation Techniques (SHAP, PDP, LIME, PFI)

Machine Learning model interpretation has been increasingly becoming more and more important as ML systems adopt more opaque algorithms and techniques. In this paper (https://arxiv.org/pdf/2007.04131.pdf), Christoph Molnar and a team of researchers take a look at the different pitfalls of using these model agnostic interpretation for machine learning models. We go through the 8 different pitfalls mentioned in the paper and their possible solutions as well. Hope you like this video and if you do, then please like, share and comment on the video. And also subscribe to the channel for more such v…