Data Science Across Domains

From Methods and Models to Business Applications

Welcome

Welcome to my portfolio:

Data Science Across Domains
From Methods and Models to Business Applications

This portfolio presents a curated collection of applied data science projects developed across different domains. Rather than a traditional theoretical text, it is organized as a series of case studies showing how modern data science methods are used to frame problems, build models, and generate practical insights.

Each chapter focuses on a specific project. Problems are clearly defined, modeling assumptions are made explicit, and solutions are developed using a combination of statistical reasoning, machine learning methods, and computational experimentation. Results are evaluated using appropriate metrics and baseline comparisons.

The emphasis throughout the portfolio is on applied problem solving. Mathematical concepts and technical details are introduced only when they help explain the modeling choices or the behavior of the algorithms being used.

Every project presented here corresponds to a fully implemented workflow. The associated computational artifacts—written in Python and R—are available alongside the text, allowing readers to explore the code, reproduce the results, and understand the implementation details behind each solution.

This portfolio reflects how data science is practiced in real environments: combining sound modeling principles, careful experimentation, and clear communication of results.

Many of the projects presented here also draw on my background in physics and quantitative modeling, where mathematical reasoning and computational experimentation naturally complement modern machine learning techniques.

Each chapter can be read independently as a standalone project, while together they illustrate a consistent approach to building and applying data science solutions across different domains.