Archive - Machine Learning Pills

Issue #104 - A/B Testing: From Hypothesis to Impact

In the world of data-driven product development, marketing, and user experience design, intuition is a starting point, not a conclusion. A/B testing, or…

Aug 17 •

Issue #103 - Context Engineering

Ever feel like your AI assistant has short-term memory loss? You give it a brilliant instruction, it performs well, but two queries later, it has…

Aug 10 •

RW #6 - Text-Moderation System with Embeddings

This week we’re handing you a plug-and-play, notebook-ready tutorial you can drop straight into Jupyter or VS Code. Inside you’ll find:Why an…

Aug 3 •

July 2025

Issue #102 - Knowledge Graphs to make RAG smarter

A knowledge graph is a structured way of representing information so that machines can interpret and reason over it. It organises entities—such as…

Jul 26 •

Issue #101 – SMOTE’s Limitations in Modern ML

In imbalanced classification problems—like fraud detection, cancer diagnosis, or spam filtering—getting the model to recognize rare cases is crucial…

Jul 20 •

and

RW #5 - No-Code Customer Service agent with LangFlow

Imagine a customer service operation where AI agents don't just rely on generic responses, but actually understand the business inside and out. Agents…

Jul 13 •

Issue #100 - Components of Time Series Data

In the world of data analysis, few things are as fascinating as watching patterns unfold over time. Whether you're tracking the daily heartbeat of stock…

Jul 6 •

June 2025

DIY #15 - Prompt Chaining with LangChain

Imagine you have a complex task, like writing a detailed report or analyzing a lengthy customer feedback document. Trying to get an AI to do it all in…

Jun 29 •

Issue #99 – Imbalanced Data in Fraud Detection

Credit-card fraud detection is the canonical “needle-in-a-haystack” problem: fewer than 1 in 1,000 transactions are fraudulent. If you train a vanilla…

Jun 22 •

and

Issue #98 - Introduction to the Model Context Protocol (MCP)

AI is evolving rapidly—but a major bottleneck still remains: how models interact with the external world. While modern large language models (LLMs…

Jun 15 •

Issue #97 - Convolutional Neural Networks

Convolutional Neural Networks (CNNs) are a class of deep learning models particularly well-suited for processing grid-structured data, especially…

Jun 8 •

Issue #96 - Correlation Heatmaps

Before training any ML model, one of your most important steps is understanding your dataset. Enter: the correlation heatmap — a visual map of…

Jun 1 •

and

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts