Data Engineering · Machine Learning / AI
MLB Intelligence Engine
A front-office analytics platform on 150 seasons of data and 8.4M Statcast pitches.
- Python
- PostgreSQL
- XGBoost
- SHAP
- Streamlit
Open to Data Engineering & Data Science roles· New York, NY
Carlos Ferrer Genao
Data Scientist | Data Engineer | AI & Analytics Developer
I build data-driven solutions, engineer pipelines, develop intelligent applications, and transform complex datasets into actionable business insights.
Carlos Ferrer Genao
M.S. Data Science · Fordham
B.S. Software Engineering · INTEC
Introduction
Data scientist with an M.S. from Fordham and a software engineering foundation, and hands-on experience across banking fraud prevention, payments and business analytics. I work across the whole data lifecycle: ingesting and modeling raw data, building pipelines and warehouses, training and explaining models, and shipping the dashboards and applications people actually use to make decisions.
More about me1M+
transactions analyzed monthly with SQL in fraud prevention
1,000+
merchants monitored by a Tableau fraud dashboard I built
20+
executive KPIs tracked in Power BI dashboards
50%
less manual reporting time through automated reports
Technical expertise
Four areas I work across, often in the same project.
Multi-source ingestion, cleaning and transformation into modeled warehouses that refresh on schedule.
Forecasting, classification and causal models — benchmarked, leakage-safe and explained with SHAP.
Executive dashboards and automated reporting built for the people who make the decisions.
LLM features where the model plans and explains, and deterministic code does the math.
Featured projects
End-to-end systems — each with its own architecture, stack and write-up.
Data Engineering · Machine Learning / AI
A front-office analytics platform on 150 seasons of data and 8.4M Statcast pitches.
Web Applications · Machine Learning / AI
Ask your sales data questions in plain English. Get answers whose numbers are checked.
Data Engineering · Business Intelligence
What should this dealership buy next, why, and at what target price?
Machine Learning / AI · Data Science
From churn probability to a named retention play with an owner and a cost.
Data Science · Machine Learning / AI
Revenue optimization built on causal inference, not just prediction.
Experience
Banking fraud prevention, payments delivery and business analytics.
Jun 2026 — Present
East Stroudsburg, PA
Build the AI, data and decision systems ownership uses to price inventory and choose what to buy.
Built a market intelligence platform (PostgreSQL, MarketCheck API, Next.js) with automated twice-daily competitor syncs that help ownership set retail prices and choose auction purchases.
Aug 2025 — May 2026
Cumberland, RI
Turned multi-source business data into executive dashboards and automated reporting.
Automated recurring reports, cutting manual reporting time by 50%.
Nov 2021 — Jan 2024
Dominican Republic
Led delivery of payment and point-of-sale projects, from planning through rollout.
Managed a point-of-sale terminal rollout, balancing cost, timeline and staffing plans across stakeholders.
Aug 2019 — Nov 2021
Dominican Republic
Investigated fraud on high-volume transaction flows and tuned the rules that catch it.
Identified recurring fraud patterns and tuned rule-based detection models, reducing false positives by 30%.
Education & certifications
Fordham University
May 2025 · Bronx, NY · GPA 3.7 / 4.0
Instituto Tecnológico de Santo Domingo (INTEC)
2020 · Santo Domingo, Dominican Republic
Data Engineering Specialization
STI Datos · 2023
Data Science Specialization
IBM · 2023
How I work
Before touching data, pin down who will act on the result and what they need to decide. It sets the grain, the metric and what "done" means.
Reconcile sources, model a clean warehouse and automate the refresh. Most analytical problems are data problems in disguise.
Leakage-safe features, benchmarked baselines and explanations attached to predictions — so results hold up when someone pushes on them.
A dashboard, an app or an automated report. The output is a decision someone can make faster, not a notebook.
Contact
I'm open to data engineering, data science and analytics roles, and to project conversations.