Homepage
Open in app
Sign in
Get started
Data Science Collective
Advice, insights, and ideas from the Medium data science community
About
Submission guidelines
Follow
Latest stories
Why Most AI Agents Fail in Production (And How to Build Ones That Don’t)
Why Most AI Agents Fail in Production (And How to Build Ones That Don’t)
I’m a 8+ years Machine Learning Engineer building AI agents in production.
Paolo Perrone
Jun 16
Part 2: Most Asked SQL Interview Questions With Real Examples (11–20)
Part 2: Most Asked SQL Interview Questions With Real Examples (11–20)
Explore the next set of must-know SQL queries often asked in data analyst interviews, explained clearly with code and context
Nishtha Prasad
Jun 15
Linguistic Fingerprints and the Future of Authorship in the Age of AI
Linguistic Fingerprints and the Future of Authorship in the Age of AI
Who Owns Writing in the Age of AI? Let’s talk about it.
Abdullah Topraksoy
Jun 15
An intuitive treatment of negative log-likelihood, cross entropy, and KL divergence
An intuitive treatment of negative log-likelihood, cross entropy, and KL divergence
For the past few months, I have been working on a follow-up to my earlier article “Understanding LLMs from Scratch Using Middle School…
Rohit Patel
Jun 15
Latest
A beginner's master guide to prescriptive analytics
A beginner's master guide to prescriptive analytics
The Analyst’s Secret to Smart Decisions (Explained)
Nishi Gandhi
Jun 14
Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents
Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents
Most AI systems today rely on fixed, human-designed architectures and can’t improve themselves over time.
Devang Vashistha
Jun 14
Uncover Hidden Patterns In Your Tabular Datasets: All You Need Is The Right Statistics.
Uncover Hidden Patterns In Your Tabular Datasets: All You Need Is The Right Statistics.
Tabular datasets can be challenging and time-consuming to analyze. However, with the right techniques and tools, you can get the most out…
Erdogan T
Jun 14
How I Built, Trained, and Deployed AI Models That Now Run My Entire Business
How I Built, Trained, and Deployed AI Models That Now Run My Entire Business
From collecting data to fine-tuning transformers, here’s how I designed AI systems that handle real tasks in the wild — with code that…
Abdul Ahad
Jun 14
How I Built a Modular JavaScript Toolkit That Runs My Entire Web Workflow
How I Built a Modular JavaScript Toolkit That Runs My Entire Web Workflow
From Dynamic DOM Manipulation to API Orchestration, My JavaScript Toolkit Controls Everything Behind My Projects
Abdul Ahad
Jun 14
What Are Ensemble Methods?
What Are Ensemble Methods?
A modern view on how collaboration improves Machine Learning
Herman Mostein
Jun 14
LangGraph + Gemini = Perplexity, But Smarter? (Free & OpenSource)
LangGraph + Gemini = Perplexity, But Smarter? (Free & OpenSource)
In this video, I have a super quick tutorial showing you how to create a multi-agent chatbot using LangGraph, Reflection, and Gemini 2.5 to…
Gao Dalie (高達烈)
Jun 14
How to Build a Beautiful Data Dashboard App on iOS Using SwiftUI Charts
How to Build a Beautiful Data Dashboard App on iOS Using SwiftUI Charts
Turn raw data into stunning visual insights with just a few lines of SwiftUI code.
Sanjay Nelagadde
Jun 14
85% of Data Scientists Ignore NamedTuples and It’s Slowing Them Down
85% of Data Scientists Ignore NamedTuples and It’s Slowing Them Down
More Readable, Faster, and Safer Than Dicts
Jaume Boguñá
Jun 14
Pandas, PySpark, or Both? A Data Scientist’s Guide to Smart Scaling
Pandas, PySpark, or Both? A Data Scientist’s Guide to Smart Scaling
Choosing the Right Tool for Scalable and Insightful Data Science
Jaume Boguñá
Jun 14
Building My Own AI-Powered Search Engine: A Deep Dive into Real-Time NLP and Ranking Systems
Building My Own AI-Powered Search Engine: A Deep Dive into Real-Time NLP and Ranking Systems
How I crafted a fully functional AI search engine from scratch using Python, embeddings, custom vector databases, and real-time language…
Abdul Ahad
Jun 14
The Comprehensive Guide to Fine-tuning LLM
The Comprehensive Guide to Fine-tuning LLM
Fine-tuning is the process of taking a pre-trained language model (a large neural network that has learned general language patterns from a…
Sunil Rao
Jun 14
Complex Systems: Unravelling the Complexity of the Unexpected
Complex Systems: Unravelling the Complexity of the Unexpected
We live in a world full of systems that are hard to understand, not only because they’re technically complicated, neither because we lack…
Alexandros Miteloudis
Jun 13
Understanding Hive Nonstrict Mode: A Complete Guide
Understanding Hive Nonstrict Mode: A Complete Guide
Introduction of modes supports by HIVE
shubham mishra
Jun 13
About Data Science Collective
Latest Stories
Archive
About Medium
Terms
Privacy
Teams