Neural networks are the backbone of deep learning. In this post, I’ll walk through building a multi-layer neural network from scratch, focusing on the math and intuition behind the process.

Customer churn is one of the most common challenges faced by businesses today. Retaining existing customers is often more cost-effective than acquiring new ones, which makes churn prediction a high-impact area for data science. In this post, I’ll walk you through how I approached this problem using logistic regression and explained the results with SHAP values.