Unbalanced data is a common occurrence for classification problems, with significant implications for model performance. In this post, we'll compare 4 different techniques for treating unbalanced data.

Understanding Backpropagation Some of the most powerful and influential machine learning algorithms are Neural Networks. They are applicable to a wide range …

This post touches on an area of growing interest in AI: Global Model Explainability. Two different approaches will be investigated in a Jupyter notebook: summed SHAP values & SAGE.

This post will cover 3 popular approaches for Hyperparameter Tuning with Random Forest Classifier. Worked examples done in Python.

We will cover the ROC and PR area under the curve metrics for evaluating a simple classifier.

Shapley Values can help explain how any machine learning model works. This post covers how they can be estimated in Python from scratch.