Contents

1. What is Explainable AI?

2. Why do we need Expalainbility?

3. Explainable Systems and Black Box Systems

4. Types of Explainability Techniques

5. Explainable Models

   1. Linear Regression

      1. Introduction

      2. Assumptions

      3. Model

      4. Statistical interpretation

   2. Decision Trees

      1. Introduction

      2. How Do They Work?

      3. Creating the model

      4. Interpretation

6. Model Agonistic Methods

   1. SHapley Additive exPlanations

   2. Surrogate model

   3. Local Interpretable Model-Agnostic Explanations and K-LIME

   4. Partial Dependence Plot

   5. Individual Conditional Plots

7. Data sets

   1. Medical cost personal Dataset

   2. Telecom Churn Dataset

   3. Sales Opportunity Size Dataset

   4. Pima Indians Diabetes Datasets

8. Implementation of these techniques on different models

   1. Logistic regression

   2. Random forest

   3. GBM - PDP

   4. GBM - ICE

   5. Deep Learning