Junior Data Engineer & Analyst | Computer Engineering Student (7th Semester) | ESPOL
I am an engineer focused on the complete data lifecycle: from building robust architectures (ETL/SQL) to analyzing trends and deploying Machine Learning models.
Unlike a traditional analyst, my technical background allows me to not only visualize data but also build and optimize the systems behind it. My goal is to transform complex raw data into clear, actionable strategies that drive business growth.
- Data Engineering: Automating ETL pipelines and optimizing database queries (40% perfomance boost).
- Machine Learning: Building predictive models for dynamic pricing and real-world scenarios.
- Business Intelligence: Identifying financial gaps ($16k+) and visualizing KPIs for decision-making.
End-to-End Data Engineering & Machine Learning Project
Simulating price optimization for ride-hailing apps (Uber/Lyft) using a pipeline that processes 1.2 Million records.
- ** ETL Architecture:** Developed an automated Python pipeline to ingest, clean, and transform 1.2 Million raw records.
- ** SQL Migration:** Migrated flat file storage (CSV) to a relational database (SQLite), optimizing queries via complex JOINs.
- ** Machine Learning:** Trained a Random Forest Regressor to predict dynamic pricing based on distance and surge multipliers.
- Tech Stack: Python, SQL, Pandas, Scikit-Learn, Matplotlib.
Award: Galactic Problem Solver (Global Nominee)
- Innovation: Built a full-stack web app analyzing 10 years of NASA satellite data to predict extreme weather probabilities globally.
- Impact: Developed in a 48-hour hackathon. Features interactive maps and real-time API integration.
- Tech: Python (Flask), React, TypeScript, Leaflet, Plotly.
Predictive Analytics for Agriculture
- Result: Projected an ROI improvement from -5.58% to +15% (+20.6 points) using historical data analysis.
- Tech: MySQL, Python, Pandas, Bootstrap.
Database Optimization & Visualization
- Achievement: Achieved 40% faster query execution through strategic database indexing and normalization.
- Scope: Analyzed performance of 15 teams across 8 LATAM countries.
- Tech: Advanced SQL, JavaScript, Chart.js.
Business Intelligence
- Insight: Identified a $16.66K performance gap between sales teams.
- Tech: Power BI, DAX, Excel.
Scientific Research
- Validation: Validated a Negative Binomial model with 309 observations (p-value = 0.660).
- Tech: R, RMarkdown, Inferential Statistics.
