Model Interpretation and Explainability: Towards Creating Transparency in Prediction Models

Model explainability and interpretability are now Explainable AI (XAI) has a counterpart in analytical being perceived as desirable, if not required, features modeling which we refer to as model explainability. of data science and predictive analytics overall. Our We tackle the issue of model explainability in the objective here is to examine what these features may context of prediction models. We analyze a dataset of look like when applied to previous research we have loans from a credit card company using the following conducted in the area of econometric prediction and three steps: execute and compare four different predictive analytics [10]. We consider the domain of prediction methods, apply the best known Lending Club loan applications. For our dataset, we explainability techniques in the current literature to perform three different analyses: the model training sets to identify feature importance 1. Model Execution and Comparison. Run and (FI) (static case), and finally to cross-check whether compare four different prediction models on the the FI set holds up under "what if" prediction