Intelligent Truck Monitoring
2024End-to-end deep learning system for real-time truck classification and license plate recognition from side-fire traffic cameras.
Computer VisionDeep LearningYOLOv8
Data Scientist & Engineer
Hi! I'm
Valentina
I build machine learning systems that turn messy, real-world data into decisions people can trust.
01 — About
Turning complex data into decisions that move the needle.
I'm a Data Scientist with a focus on machine learning and deep learning. I graduated from the City College of New York in 2025 with a Master's in Data Science and Engineering.
From deep learning pipelines for intelligent traffic monitoring to automated data ingestion systems, I care about building models that are accurate, reliable, and genuinely useful — handling class imbalance, engineering features, and rigorously evaluating performance along the way. I'm currently building out a portfolio of machine learning projects and data visualization work, which I'm sharing here.
MScData Science & Engineering
The City College of New York
The City College of New York
02 — Projects
Selected work
Automated Data Ingestion Pipeline
2024A scalable web scraping and ingestion pipeline that extracts, filters, deduplicates, and stores structured data at scale.
NLPData EngineeringPython
Infrastructure Anomaly Detection
2021Analysis of large maintenance datasets to surface operational inefficiencies and anomalous patterns across civil assets.
Data AnalysisPredictive ModelingPandas
03 — Experience
Where I've worked
Feb 2025 — Jul 2025
Graduate Research Assistant — Transportation Lab
The City College of New York · New York, NY
- Designed and deployed a deep learning pipeline (CNN + LSTM + YOLO) for intelligent truck activity monitoring using side-fire camera footage.
- Developed data analysis algorithms to optimize urban transportation networks for ongoing research.
- Collaborated with a multidisciplinary team to prepare findings for publication and conference presentations.
Oct 2021 — Jul 2022
Project Management Analyst
Cabarco S.A.S · Cali, COL
- Analyzed large operational datasets on schedules and budgets, improving project execution efficiency by 20%.
- Designed automated reporting systems to monitor progress in real time and ensure deadline and cost compliance.
Aug 2020 — Feb 2021
Civil Engineering Intern
Ecopetrol S.A · Medellín, COL
- Analyzed maintenance datasets in Python (Pandas, NumPy) to identify inefficiencies and anomalous patterns across assets.
- Built visualizations with Matplotlib and Seaborn to support engineering decision-making.
04 — Contact
Let's build something with your data.
Open to data science roles, research collaborations, and interesting problems. Drop a message or reach me directly.
vsambonirougerio@gmail.com