Growth, Product & Customer Analytics
Understanding acquisition, engagement, and lifetime value through funnel analysis, experimentation, and customer insights.
Hi, I'm Gabriel Reynoso
Data Scientist | Growth, Product & Customer Analytics
I combine business judgment with technical depth to understand customers, evaluate what works, and build data solutions that support better product and growth decisions.
About Me
I combine a foundation in engineering, mathematics, and data science with hands-on experience guiding growth, product, and customer decisions.
At Klar, I led a team of six analysts working on referrals, customer engagement, and lifetime value. Earlier roles at Ben & Frank and Ford gave me experience building data pipelines, automating processes, and developing analytics tools for business teams.
I hold degrees in Mechatronics Engineering and Industrial Engineering from ITAM and am currently completing an MS in Data Science at Stevens Institute of Technology. I'm especially interested in how customer behavior, experimentation, and machine learning can inform product and commercial decisions.
Outside work, I'm an avid reader and sports enthusiast. I'm curious by nature and enjoy exploring new ideas, both within data science and beyond it.
Technical Toolkit
Applied Machine Learning
Developing predictive models and simulations, with attention to evaluation, uncertainty, and the decisions they support.
Data Engineering & Automation
Building data pipelines, integrating business data, and automating workflows that make analysis useful in everyday operations.
Technical Skills
The tools and methods I use to explore data, build solutions, and support business decisions.
Programming & Data Analysis
Statistics & Machine Learning
Data Engineering & Cloud
AI-Assisted Development
Featured Projects
A selection of projects exploring predictive modeling, optimization, and engineering problems.
FIFA World Cup Forecasting
A two-stage probabilistic forecasting system for the 2026 World Cup, combining a Dixon-Coles match model with a LightGBM calibrator and a Monte Carlo tournament simulation.
- 0.8711 test log-loss, +20.7% vs. uniform baseline
- Evaluated on 4,552 held-out matches (2022+)
- 100,000-run Monte Carlo tournament simulation
Traffic Optimization via Collective Intelligence
Comparing greedy routing, marginal-cost assignment, and a Q-learning agent trained by expert imitation on a real Manhattan street network.
CodeHeterogeneous Teleoperation for Remote Engineering Education
Undergraduate thesis on a teleoperation system for remote engineering labs, recognized with ITAM's Best Thesis Award.
- Best Thesis Award — XXVI Premio de Investigación ExITAM, 2021