A comprehensive resource on practically every topic for data science researchers — Edit: the compendium has its own website @ mlcompendium.com and the google doc is now fully retired in favor of the website. …

Using LLMs as black box classifiers — I was curious to understand how Scikit-LLM works in practice. According to the repo’s author, Scikit-LLM integrates powerful language models like ChatGPT into Scikit-learn for enhanced text analysis tasks. Looking at the backend, it seems that it simply wraps zero-shot prompts for multi-class and multi-label classes. …

The simplicity of using an LLM for data understanding It seems that finding novel uses for LLMs is one of our community’s hobbies. Pandas-AI is a Python library that integrates generative artificial intelligence capabilities into Pandas, making data frames conversational. …

Prompt engineering’s hidden costs — Democratizing LLM and foundation models is probably one of the greatest achievements in the last few years. …

So you want to be a data science product manager? — Aspiring product managers (PMs) sooner or later would like to change career paths and move toward the data domain. However, there is a gap in knowledge and experience that needs to be bridged. …

The intricate relationship between DS teams, ML engineering & production independence — These days the role of a Machine Learning Engineer (MLE) is becoming a necessity. Data science (DS) teams can’t operate independently and reach production without an MLE who practices MLOPs, i.e., without an MLE there is a good chance that DS teams will not be able to reach production. There…

Common problems that you will experience if your ML feature is not free — In many companies, where machine learning (ML) is not the core business, there is a tendency to place ML as gated features, i.e., features that are only accessible if you pay more for them, i.e., as a way to upsell a product. In this article, I will argue that ML…

By providing data, product & ML engineering functions — It seems like every company wants to have its own data-science (DS) team in order to bring additional value in ways that can’t be achieved with traditional methods. In this short article, I’ll cover the three pillars of what a DS team needs in order to succeed & thrive (Figure…

An easy approach for monitoring your ML models — We all know by now that data & model monitoring is extremely important. Even if your production-ready model didn’t change, the data distribution may have and it had potentially affected your outputs, which directly influenced your users, and once this happened you potentially have a client-facing production problem. This article…