Skip to content
View rodnm's full-sized avatar

Highlights

  • Pro

Block or report rodnm

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please donโ€™t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
rodnm/README.md

Hi, I'm Rodrigo Norabuena ๐Ÿ‘‹

Quantitative researcher who builds the data infrastructure to answer the questions.


๐Ÿงญ About Me

I'm an Economist (PUCP, 2024) who works across the full data lifecycle โ€” from defining the right question and choosing the right methodology, to building the pipelines and models that produce the answer.

My background in statistics and econometrics gives me a rigorous foundation for empirical research and causal analysis. My experience in data engineering means I can design and automate the infrastructure that makes that research possible. And my growing work in machine learning and AI engineering lets me apply modern techniques to real-world problems โ€” not just as tools, but with an understanding of when and why they're appropriate.

At CENTRUM PUCP I design relational databases, build end-to-end ETL processes in Python, and develop AI-powered tools for institutional workflows. Previously as Marketing Director at Revista Econรณmica PUCP, I combined data analysis and visualization to drive editorial decisions.

  • ๐Ÿ† Finalist at Datatรณn OEFA 2025 โ€” predictive model for dengue outbreak detection using environmental data
  • ๐Ÿ“š Enrolled in AI Engineer and Multicloud Data Engineer specialization programs
  • ๐Ÿ”ญ Currently expanding my portfolio with ML pipelines, RAG systems, and economic forecasting models
  • ๐ŸŒŽ Based in Lima, Perรบ โ€” open to data science, analytics, and data/AI engineering roles

๐Ÿš€ Featured Projects

Bibliometric analytics pipeline with a live interactive dashboard

  • Designed a modular ETL pipeline using Medallion Architecture (Bronze / Silver / Gold) orchestrated with Apache Airflow on Docker
  • Ingests data from the OpenAlex API and surfaces it through a Streamlit dashboard with dynamic filters by field, year, and institution
  • Stack: Python ยท Pandas ยท Plotly ยท Airflow ยท Docker ยท Streamlit

Real-time crypto market tracker with interactive visualizations

  • Built a real-time ETL system that fetches and processes cryptocurrency data from the CoinGecko API
  • Features a treemap of market cap, 7-day trend charts, and a dynamic theming system
  • Stack: Python ยท Streamlit ยท Plotly

Exploratory analysis of rare earth trade flows (1995โ€“2022)

  • Analyzed global rare earth trade data from OEC, mapping top exporters, importers, and trade balances by country
  • Built an interactive Power BI dashboard published to Power BI Service, with data cleaning and transformation in R
  • Stack: R ยท Power BI ยท DAX

๐Ÿ› ๏ธ Tech Stack

Languages

Python R SQL Stata MATLAB

Data Engineering

Apache Airflow Apache Spark Databricks Docker PostgreSQL SQL Server

Statistics & Econometrics

Statsmodels SciPy scikit-learn NumPy Pandas

AI & Machine Learning

PyTorch HuggingFace FastAPI Ollama

Cloud

AWS GCP Azure

Analytics & Visualization

Power BI Streamlit Plotly

Tools

Git GitHub n8n Quarto


๐Ÿ“Œ Currently Building

Project Description Status
๐Ÿค– End-to-end ML pipeline MLflow + FastAPI deployed model ๐Ÿ”จ In progress
๐Ÿ“š RAG pipeline LangChain + ChromaDB document QA ๐Ÿ”จ In progress
๐Ÿ“Š Customer segmentation Churn model + RFM segmentation ๐Ÿ—‚๏ธ Planned
๐Ÿ“‰ Economic forecasting Time-series with Peruvian public data ๐Ÿ—‚๏ธ Planned

Open to data science, analytics engineering, and AI roles in Lima, Perรบ.

LinkedIn ยท Portfolio ยท Email

Pinned Loading

  1. rodnm.github.io rodnm.github.io Public

    Sitio web personal.

    HTML

  2. openalex-research-dashboard openalex-research-dashboard Public

    Modular ETL pipeline and interactive dashboard for analyzing OpenAlex bibliometric data, featuring research trends, leading authors, key institutions, and influential works across multiple fields oโ€ฆ

    Python

  3. crypto-monitor crypto-monitor Public

    Real-time ETL system that collects and processes live cryptocurrency market data from the CoinGecko API to support analytics and automated dashboards.

    Python

  4. project_powebi_rare-earth project_powebi_rare-earth Public

    R 1

  5. diognes/Rseries diognes/Rseries Public

    R 1

  6. bcrp-tasa-de-cambio bcrp-tasa-de-cambio Public

    Web scrapping de series de la tasa de cambio del dรณlar - Venta.

    R 1