A results-driven Data Scientist and Machine Learning professional passionate about building end-to-end predictive pipelines, optimizing statistical models, and translating complex mathematical architectures into actionable corporate insights.
- Graduate with a Bachelor's degree in Economics, fully studied in English at University Carlos III.
- Graduate with a Master's Degree in Data Science, specializing in predictive modeling, advanced classification algorithms, feature engineering, and automated hyperparameter optimization.
- Core expertise lies in designing robust statistical workflows, benchmarking algorithmic performance, handling class imbalance, and maximizing critical operational metrics (such as sensitivity and recall).
- Currently exploring distributed learning infrastructures, production-level MLOps architectures, and advanced cluster-segmentation modeling.
Here is a selection of my core data science, machine learning, and data engineering projects:
Social Ads Purchase Prediction
Algorithmic classification benchmarking and automated hyperparameter optimization using GridSearchCV. Features advanced data scaling and pipeline engineering to maximize target operational recall scores.
Traffic Accident Analysis in Madrid
Consolidation and deep exploratory data analysis (EDA) of a multi-year municipal corpus encompassing over 312,000 records to isolate statistical distributions and feature correlations for road safety.
Global Emissions & Climate Change
Statistical transformation, custom multi-variable reshaping, and data cleaning using advanced functional pivoting techniques to isolate specific environmental pollution metrics by industry.
Car Depreciation & Market Value
Detailed statistical profiling and data cleansing pipeline on automotive marketplace transactions, implementing domain-specific outlier filtering and mathematical target stabilization.
Streaming Platform Content Analysis
Cloud-ready big data engineering pipeline targetting compressed columnar metadata and nested arrays to track international streaming production hubs and release timeline trends.
Telecom Customer Churn Prediction
Application of advanced statistical inference, logistic regression, and predictive regularization models (Ridge and Lasso) using cross-validation to prevent user attrition and handle corporate dataset balancing.
End to End Ticketing BI Pipeline
Design of a complete data warehouse infrastructure using a medallion architecture (bronze, silver, gold) to isolate data extraction and monitor service level agreements (SLA) alongside internal backlog dynamics.
En camino... 🛠️
Space reserved for upcoming advanced predictive models, clustering frameworks, or neural network architectures.
Statistical inference, robust feature engineering, classification benchmarks, and cluster analysis. Expert implementation of cross-validation techniques and hyperparameter optimization to drive real-world KPIs.
Pipeline automation and architecture development. Building medallion data infrastructures, distributed data tasks using Spark, and scalable ETL/ELT workflow optimization.
Transforming dimensional data models into relational executive summaries. Expert management of advanced data cleaning, relational schemas, and interactive reporting dashboards.
al1sr