Ivan Perez Avellaneda
I’m a data-driven problem solver with a Ph.D. in Electrical Engineering and a strong foundation in mathematics, economics, and nonlinear systems. Currently working as an Analytics Engineer at Monaghan Medical Corporation, I apply advanced analytics and modeling techniques to improve operational efficiency and strategic decision-making.
My doctoral research focused on data-driven reachability analysis of nonlinear systems, bridging control theory, optimization, and AI safety. I’m passionate about translating complex mathematical frameworks into scalable, intelligent solutions—whether in business, finance, or engineering domains.
With experience across academia, healthcare, and financial sectors, I’ve applied tools from machine learning, operations research, and statistical modeling to solve real-world challenges. I’ve also co-taught university-level courses in mathematics and control systems, reinforcing my commitment to clear communication and technical leadership.
Main Interests:
- Nonconvex and constrained optimization
- Optimal control and calculus of variations
- Machine learning, AI interpretability, natural language processing (NLP)
- Time-series analysis and predictive modeling
- Symbolic computation and formal methods
Education:
- Ph.D. in Electrical Engineering – University of Vermont (2023)
- M.Sc. in Economics – Pontifical Catholic University of Peru (2018)
- B.Sc. in Mathematics – Pontifical Catholic University of Peru (2016)
Session
The problem of address matching arrives when the address of one physical place is written in two or more different ways. This situation is very common in companies that receive records of customers from different sources. The differences can be classified as syntactic and semantic. In the first type, the meaning is the same but the way they are written is different. For example, one can find "Street" vs "St". In the second type, the meaning is not exactly the same. For example, one can find "Road" instead of "Street". To solve this problem and match addresses, we have a couple of approaches. The first and simple is by using similarity metrics. The second uses natural language and transformers. This is a hands-on talk and is intended for data process analyst. We are going to go through these solutions implemented in a Jupyter notebook using Python.