ALICE: Combining Feature Selection and Inter-Rater Agreeability for Machine Learning Insights
It offers a tool for improving interpretability in ML, but appears incremental as it merges existing concepts into a user-friendly framework.
The paper introduces ALICE, a Python library that combines feature selection with inter-rater agreeability to provide insights into black-box machine learning models, with initial experiments on a customer churn prediction task.
This paper presents a new Python library called Automated Learning for Insightful Comparison and Evaluation (ALICE), which merges conventional feature selection and the concept of inter-rater agreeability in a simple, user-friendly manner to seek insights into black box Machine Learning models. The framework is proposed following an overview of the key concepts of interpretability in ML. The entire architecture and intuition of the main methods of the framework are also thoroughly discussed and results from initial experiments on a customer churn predictive modeling task are presented, alongside ideas for possible avenues to explore for the future. The full source code for the framework and the experiment notebooks can be found at: https://github.com/anasashb/aliceHU