Author: Scott King
-
Regression Models: When You Need to Predict Actual Numbers
Learn when to use regression models instead of classification. Build customer lifetime value predictions using Linear Regression, Ridge, and Random Forest. Understand MAE, RMSE, and R² metrics with practical Python code.
-
Build vs. Buy for Data Products: A Decision Framework
A practical decision-making framework covering total cost of ownership, time-to-value, maintenance overhead, and when custom solutions actually make sense.
-
ML Fundamentals: Stop Overthinking, Start Building
Learn machine learning fundamentals by building a spam classifier in 30 minutes. Same techniques apply to customer churn and employee attrition prediction. No PhD required—just Python and practical code.
-
Classification Models: Pick the Right Tool
Compare four classification algorithms on the same churn dataset. Learn when to use Logistic Regression, Decision Trees, Random Forest, or XGBoost. Understand the performance vs interpretability tradeoff and make principled choices based on business context.
-
Data Prep: Where ML Projects Actually Live or Die
Master the 80% of ML work that happens before modeling. Handle missing values, scale features, avoid data leakage, and build proper train/test splits. If your model performs terribly, it’s probably your data prep.
-
Building a Data Team from Scratch: Hiring, Structure, and Culture
A practical guide to hiring data engineers, analysts, and scientists, with insights on team structure, compensation benchmarks, and building an effective data culture.
-
Building and Serving ML Models in Snowflake
A practical, no-nonsense guide to building machine learning models in Snowflake and deploying them at scale. Learn how to train models where your data lives and serve predictions directly in SQL.
-
Building AI Apps Just Got Way Easier: Microsoft’s AI Toolkit for VS Code
If you’ve been curious about building AI-powered applications but felt intimidated by the complexity of setting up models, managing APIs, and juggling different AI platforms, Microsoft just dropped something that might change your mind. The AI Toolkit for VS Code gets a lot of things out of your way and simplifies the process. What’s All…
-
Common AI Implementation Costs
If you’re thinking about jumping on the AI bandwagon, that could be a smart move. But before you start dreaming about robot assistants handling all your mundane tasks, let’s talk frankly about what this AI adventure is actually going to cost you. Spoiler alert: it’s probably more than you think, but don’t let that scare…
-
The General-Purpose CrewAI Template: Everything in One File
Update: I had originally posted this before, but decided to make a few changes to the template: namely, adding functions and putting everything into a class. This is the new version. CrewAI enables developers to orchestrate teams of AI agents that work together to solve complex problems. Instead of managing multiple files and complex project…
-
A Review of Snowflake Snowpark
After spending several months using Snowflake Snowpark, I’m really impressed with how it enhances the data engineering and data science experience within the Snowflake ecosystem. Essentially, Snowpark allows you to write and execute code directly inside Snowflake using languages like Python, Scala, and Java. This eliminates the need for external processing engines, which reduces complexity…
-
CrewAI: Multi-Agent Systems Made Simple
Build multi-agent AI systems with CrewAI’s Python framework. Learn how to orchestrate autonomous agents that collaborate to solve complex tasks and automate workflows.
-
Running LLMs on Your Own Machine: A Quick Guide to Ollama
Set up Ollama to run LLMs like Llama and Mistral locally on your machine. Skip API costs and keep your data private with this step-by-step local LLM guide.
-
Getting Data Into PyTorch Tensors
Master PyTorch tensor data loading without the frustration. Learn practical techniques for converting NumPy arrays, lists, and datasets into PyTorch tensors efficiently.
-
Getting Started with PyTorch
So you want to get into machine learning and everyone keeps talking about PyTorch? Good choice! PyTorch is basically the cool kid on the ML block right now, and for good reason – it’s way more approachable than you might think. Pytorch doesn’t force you to think like a computer. You can build and tweak…