Data Scientist

Diagnose, structure, organize, and analyze financial datasets. Develop statistical and predictive models for demand forecasting and supply optimization using Python and R. Build and maintain regression, LightGBM, and random forest models, improving accuracy through better data cleaning and web scraping pipelines. Optimize combinatorial and network optimization algorithms, design interactive Shiny dashboards, and collaborate with clients and stakeholders to translate model outputs into actionable insights.

Designed a relational database schema, led stakeholder discovery with HR and finance teams, developed a Dash application for data visualization with role-based access controls, built an ETL pipeline to migrate Excel datasets into a SQL database, and created technical documentation and a methodology manual.

Designed and deployed a financial data management and visualization tool using Python and Streamlit. Built an ETL pipeline from Google Drive via Google Cloud APIs into a relational SQL database, conducted stakeholder meetings to define dashboard requirements, and published a sanitized portfolio version on GitHub.

Structured raw field research data into clean datasets using Python and performed descriptive statistical analysis, hypothesis testing, and visualization across three formal reports.

Defined and implemented a custom combinatorial optimization algorithm in Python to minimize industrial cutting costs, achieving significant cost savings and eliminating material waste. Created visual operational maps and presented the mathematical solution to non-technical production staff.

Bachelor's degree with a thesis in combinatorial optimization focused on solving the Capacitated Vehicle Routing Problem (CVRP).