Data Scientist and Applied Mathematician specializing in predictive modeling, statistical inference, and survey design. Experienced across the end-to-end data lifecycle: database design and data modeling, rigorous quantitative analysis, and deploying machine learning models focused on measurable business impact.
Predictive modeling, survey calibration, unsupervised clustering, and financial NLP
End-to-end Machine Learning pipeline to predict customer attrition from transactional and behavioral data, addressing class imbalance, optimizing decision thresholds with PR-AUC, and generating explainability via SHAP values.
Inferential analysis on complex surveys with design corrections and expansion weights, non-response adjustments (weighting classes, propensity scores), and weighted linear/logistic models with Taylor linearization standard errors.
Transactional data processing, feature engineering (Recency, Frequency, Monetary value), and unsupervised clustering using K-Means optimized via Elbow and Silhouette scores deployed on an interactive dashboard.
Data extraction and cleaning from news sites, forums, and social media for training and prompting Large Language Models (LLMs and Transformers) to analyze financial sentiment and market trends across stocks and cryptocurrencies.
Predictive modeling in industry and teaching in probability and statistical inference at UNAM
Expertise across analytical databases, quantitative languages, machine learning, statistical methods, and developer tooling
Rigorous academic mathematical training at UNAM and industry-recognized certifications
Analytical training in applied probability, mathematical statistics, optimization, and scientific computing.
Data cleaning, analysis, visualization, and key tools for machine learning and artificial intelligence (Scikit-Learn, SciPy, NumPy, Pandas, Folium, Seaborn).
Analytical skills (data cleaning, analysis, and visualization) and key tools (spreadsheets, SQL, R programming, Tableau).