Data Science Collective

Welcome to Data Science Collective, a community-driven publication dedicated to exploring data science through writing. We’re to highlight…

Smoothing data using local regression

Join Data Science Collective

Llama 1 can be regarded as the first open-source large language model that can compete with ChatGPT after the emergence of ChatGPT. Llama 1…

(Non-Member Link)

A Practical, High-Performance, and Interpretable Decision Tree Approach Incorporating Autoregressive Lags, Seasonal Dynamics, and…

Coding a Web Scraping Agent Using Playwright MCP

The statistics behind why parallel parking is always so cursed

A hands-on, into the core math behind attention — building a minimal yet functional Transformer using only pure Python.

How to Set Up LLMs on Your Machine in Just a Few Minutes

The Building Blocks for Streamlining Complex Data Science Workflows.

Game theory reveals surprising pessimism when AI models simulate regulatory scenarios

The Importance of Building a Benchmark and How To Do It

How combining foundational and non-foundational models can take forecasting further

A generalized version of Kaplan-Meier allows to model a continuous value (like money) instead of a binary signal (like survival)

Or, how an urban planner’s simple method competed against more technical projects

If you are not a paid member on Medium, I make my stories available for free: Friends link