Aitor Bazo | Data Scientist / Analyst / Developer

Python • Pandas • Machine Learning • Statistical Analysis • Data Visualization • Automation & LLM Workflows

I specialize in data analytics, with a focus on uncovering actionable insights from complex datasets. My expertise includes programming, data visualization, and the use of statistical methods to inform strategic decision-making. I have worked on several projects across various industries and have experience in cleaning and analyzing large datasets, data wrangling, data visualization and presentation, machine learning, and process automatization. Based in Peru, remote, with Spanish/EU citizenship.

Projects

canary-ml

Watches production ML models for drift and anomalies in real time, no extra infrastructure.

Python · SciPy

havoc-monkey

Deliberately breaks data pipelines in controlled ways to catch failures.

Python · PyPI

fin_dash

Turns a trade log into risk-adjusted performance metrics.

Python · Pandas

FAO Yields

Compares how efficiently each country turns farmland into crop yield.

Python · Streamlit

pau pau

Self-building CLI agent that writes and improves its own Python tools.

Python · CLI

stripify

Analyzes your Spotify listening history and uses GPT to recommend what to play next.

Python · GPT

Res Domus

Inventory, spending, and stock tracking, with document parsing and a built-in AI assistant.

Python · SQL

Live Stock Charts

Playful old thing. Interactive live charts for NYSE companies.

Google Sheets · No-code

Skills

Python Pandas NumPy SQL Machine Learning Keras Forecasting Statistics Anomaly Detection NLP LLM Prompting Agentic Workflows Agent Orchestration / MCP Automation / Scripting APIs Data Visualization Tableau Excel Google Sheets Jupyter Git Linux OOP

Experience

2012–ongoing

Independent Data Scientist & Analyst

Applied ML and statistical analysis in a self-directed practice involving real-time data processing and Keras-based decision systems. Built Python/Pandas/NumPy pipelines automating >4M-row datasets, with dashboards for model evaluation and feature engineering. Layered in LLMs and NLP as those tools matured.

2023–2024

Operations Analyst, Multilingual

Automated Google Sheets pipelines, halving manual reporting time. Monitored KPIs and reported to stakeholders. Coordinated remote collaboration across three continents via Slack, Trello, and Zoom.

Education

B.Arch

Universidad Peruana de Ciencias Aplicadas

Advanced Data Analytics Certificate

Google

Certificate of Advanced English (C1)

University of Cambridge