It would be based on the following papers - [check this paper](https://homes.cs.washington.edu/~marcotcr/aaai18.pdf) - [General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Models](https://arxiv.org/pdf/2007.04131.pdf) - [Fooling LIME and SHAP](https://dl.acm.org/doi/pdf/10.1145/3375627.3375830) - [A Human-Grounded Evaluation of SHAP for Alert Processing](https://arxiv.org/pdf/1907.03324.pdf) - [ ] adding summary of papers - [ ] adding a notebook