Data Science Collective

Or … how an ML library can accelerate Non-ML computations

Here’s how I turned Python into a personal operating system — managing my files, emails, invoices, schedules, and even reminders without…

What I learned building a full content performance tracker in Power BI from scratch

As a product manager at a fast-growing tech company, I spend a significant portion of my day navigating through Google Docs filled with…

Explore how graph databases and Cypher queries reveal powerful connections in your data.

Difference-in-Differences (DiD) is a widely used technique to estimate causal effects when randomized experiments are not feasible. From…

🔍 The untold journey of creating a 2B-parameter marvel that competes with LLM behemoths in precision, speed, and practicality — and what…

Data tells a story — but who writes it? Learn how the strategic choice of metrics and reference points can change the entire narrative.

Clustering Home Health Agencies by Cost and Quality in 2025

Last year there was a lot of speculation about when and how LLM providers would integrate advertising into their services. Not necessarily…

A fictional but practical look at how AI agents — powered by the ESCO taxonomy— could support human decisions after a merger

Qwen-v1 is a large model launched by Alibaba Group. It has introduced multiple Qwen models adapted to different tasks, including Code-Qwen…

Introducing PredictiQ, a benchmark designed to test, how well large language models (LLMs) can perform predictive data analysis.

Streamline dataset discovery and management using the Kaggle API.

A breakdown of the three fundamental math fields required for machine learning: statistics, linear algebra and calculus.

A simple example illustrating the power of text embeddings

A content repurposing tool built with Python and AI to extend your voice, not replace it.