Data science and applied AI notes

About this blog

I write about the reasoning behind practical data work: how to frame analytical questions, understand statistical models, evaluate machine-learning systems, and connect technical results to decisions. These notes range from accessible explanations to hands-on explorations of real datasets.

The collection currently covers deep learning, mixed-effects models, statistical testing, useful data-science references, and patterns in Python package adoption. New articles will increasingly explore AI agents, evaluation, geospatial analytics, experimentation, and trustworthy analytical workflows.

Rather than treating tools as the starting point, the articles focus on questions: what assumptions a method makes, what evidence supports a conclusion, which failure modes matter, and how an analysis could change a real decision. Some posts are short conceptual guides; others use code, visualisations, or public data to investigate a specific pattern.

The intended audience includes analysts, data scientists, researchers, product teams, and curious readers who want a clearer view of how data methods work in practice. Posts may be written in English or Arabic, reflecting the languages in which I learn and communicate. Use the language selector to browse the available collection and return as new practical notes, experiments, and research summaries are published.