ABOUT ME

Economist with a specialization in Social Sciences, graduate of the Pontificia Universidad Católica del Perú (PUCP, by its acronym in Spanish), and currently pursuing a Master's degree in Data Science and Artificial Intelligence at the Universidad de Ingeniería y Tecnología (UTEC, by its acronym in Spanish). I possess solid knowledge in statistics, machine learning, deep learning, and applied data science, supported by certifications such as the Data Analyst Professional (V2) and specializations in Web Scraping and Advanced Data Science.

I am proficient in key tools and platforms such as Python, R, SQL/PLSQL, Power BI, Databricks, GCP, AWS, and GitHub. My technical skills are complemented by experience with statistical software (Stata, SPSS), geographic information systems (ArcGIS, ArcGIS Pro), and programming languages such as MATLAB and GAMS. I also have extensive experience in data visualization using Tableau, Power BI, and Looker Studio.

WORK EXPERIENCE

• Economic Consultant – Ministerio de la Producción del Perú (2024 – Present)
• Data Analyst – Equilibrium SDC (2023 – 2024)
• Data Analyst – MIDE Development (2022 – 2023)
• Research Assistant – CISEPA PUCP, Universidad del Pacífico, and with PhD. Mario Tello (2020 – 2022)
• Teaching Assistant – Pontificia Universidad Católica del Perú (2020)

PORTFOLIO

Credit Scoring Using Psychometric Traits and Machine Learning

This project explores the use of psychometric assessments to predict credit behavior among micro-entrepreneurs. Based on the Big Five personality traits, the model aims to classify individuals as good or bad payers, offering an inclusive alternative to traditional credit scoring.

Technologies: Python, pandas, scikit-learn, XGBoost, NumPy, Matplotlib, Seaborn

View on GitHub

Optimizing Debt Collection Campaigns with Behavioral Insights

This project analyzes telemarketing campaign data to identify a 4% drop in contactability. Behavioral patterns were analyzed to improve outreach strategies and reduce call costs.

Technologies: Python, pandas, scikit-learn, XGBoost, NumPy, Matplotlib, Seaborn

View on GitHub

Real Estate Market Analysis via Web Scraping on Facebook Marketplace

This project scrapes rental listings from Facebook Marketplace to analyze apartment rental prices in Lima. Data is visualized using bar plots to show price patterns.

Technologies: Python, Splinter, BeautifulSoup, pandas, re, Matplotlib

View on GitHub

YouTube Sentiment Data Extraction Using Public APIs

This Python script uses the YouTube API to extract comments from a specific video and saves them into a CSV file. Ideal for sentiment analysis or audience research.

Technologies: Python, YouTube Data API, googleapiclient, configparser, csv

View on GitHub

Automated Retrieval of Public Tax Records from SUNAT using DNI

This project performs web scraping on Peru's tax agency (SUNAT) website to retrieve individual data using their national ID numbers (DNI). It uses public data from a government merit contest as input.

Technologies: Python, Selenium, pandas, re, time, ChromeDriver

View on GitHub

Business Data Mining from Google Maps with Playwright

This project demonstrates how to use Playwright in Python to automate data extraction from Google Maps listings. The script collects business name, address, website, phone, and reviews, storing them in both Excel and CSV formats. Useful for building local business databases.

Technologies: Python, Playwright, Pandas, Dataclasses, Selenium

View on GitHub

CONTACT