CV

Education

• M.S. in Mathematical Modeling, Statistics, and Computation, University of the Basque Country
• M.S. in Applied Mathematics, Santo Domingo Institute of Technology
• B.S. in International Business & Finance, Utah State University

Work experience

• 2023-2024: Data Scientist, Promotion Optimization (BEES)
  • AB InBev
  • Duties included:
    • Collaborated with regional LATAM team on a promotion optimization algorithm, improving key metrics like ROI, investment, and coverage across various promotional strategies (combos, stepped, among others).
      • This involved modeling demand elasticity with a log-log model (XGBoost), optimizing for a chosen metric with cubic splines, rank suggested order arrangements in combos, among other phases.
    • Optimized ROI by 48% in A/B test promotional experiments in the market of Panama, over a period of 8 months.
    • Developed an algorithm targeting first-time purchasers, optimizing discount allocation and saving on budget.
    • Designed and implemented causal inference models (X-Learner, T-Learner, Synthetic DiD) to assess market innovation impacts (ATT, CATE), enabling trend identification at the blocking factor level.
• 2022-2023: Data Scientist, Product Recommendation
  • Santa Cruz Bank
  • Duties included:
    • Optimized the product recommendation (NBA) feature pipeline from having < 20 to > 50 variables, into a collaborative filtering, ranking, and ensemble learning approach.
    • Enhanced customer segmentation by incorporating digital behavior clustering and psychographic profiling based on commerce data.
    • Automated weekly client account reporting via a data pipeline job, boosting productivity 3x and eliminating manual data wrangling.
    • Applied NLP techniques (sentiment analysis, n-grams, entity classification) to extract insights from Salesforce CRM interaction data.
• 2019-2022: Data Scientist, Risk Analytics
  • Dominican Tax Administration
  • Duties included:
    • Collaborated in developing the analytics & machine learning feedback system to label taxpayers as risky or not risky.
    • Mapped shareholding structures using graph theory (NetworkX, Bokeh) to identify central entities and uncover hidden transactional relationships, improving the detection and prioritization of tax evasion cases by 2x.
    • Built models such as linear regression, decision trees, PCA, and clustering.
    • Created the Data Warehouse inventory eCatalog, a Shiny (R) solution mapping all data infrastructure used for risk estimations (metadata, data dictionaries, data lineage). This streamlined the process of identifying data sources by 5x.

Skills

• Git
• Python
• R
• Data Science & AI Techniques: Propensity score matching (PSM), A/B/n testing, RCTs, synthetic controls, regularization, among others.
• Spark
• MLflow
• Azure Cloud: Azure Databricks, Azure Machine Learning Studio, Azure DevOps, and Azure Synapse Analytics. AWS: Amazon SageMaker, Amazon Redshift, Athena, AWS Glue.
• Additional Tools: SQL, MATLAB, Java, CPLEX, Gurobi, PuLP.

Leadership

• AB InBev Analytics Workshop Professor (2024)
• AB InBev Global Hackathon (2023)
• R Programming Mentor (2022-2023)

Last updated: 2025-06-04