Towards Data Science

A new kind of hyperparameter study

How to structure decisions, identify efficient options, and avoid misleading value metrics

An analysis of how flattening structured data can boost precision and recall by up to 20%

Going beyond the math to build intuition

Confessions of a vibe coder

Randomization usually balances confounders in experiments, but what happens when it doesn’t?

Implementing cross-silo federated learning step by step

From notebooks to real-world systems

Recognize data science as an engineering practice and structure education accordingly.

Learning audio embeddings with contrastive learning and deploying them in a real music recommendation app

Why specialized models still hold the 30x speed advantage in production environments

How prompt engineering has evolved, examined scientifically; and implications for the future of conversational AI…

How to evaluate goal-oriented content designed to build engagement and deliver business results, and why…

Google Trends is one of the most widely used tools for analysing human behaviour at…

How I used open-source models to explore new frontiers in efficient code generation, using my…

Why modeling SKUs as a network reveals what traditional forecasts miss

Do you know where your data has been?

Let’s zoom in on recent approaches that push AI-powered workflows to the next level

Let’s make sense of the current state of retrieval-augmented generation

Estimating neighborhood-level pedestrian risk from real-world incident data

Explore a practical approach to analysing massive datasets with LLMs

How relationship-aware graphs turn connected forecasts into operational insight

An accessible introduction to causal inference and ML

An introduction to neural machine translation

A deep dive on data transfer bottlenecks, their identification, and their resolution with the help…