Paper Title
Machine Learning Frameworks for Attribute Analysis Algorithms and Explainability of Classification Models

Abstract
Across various machine learning models applied on a variety of datasets for the purposes of classification, it is not clear why the machine learning models make the decisions they do. We need to find a way to increase interpretability and transparency of classification decisions of machine learning models. This solution can help to analyze decisions of machine learning models to decide which models to use and find better ways to make machine learning models more accurate at classification tasks.