Transform Heterogeneous Data Into Predictive Insight

I am a data scientist and transportation system modeler with a PhD in Engineering Science (Mobility and Industrial Management) and more than a decade of experience.  My work sits at the intersection of data science, statistical modeling, and machine learning, with a strong emphasis on understanding, modeling, and improving complex systems using real-world data, primarily in the context of transportation systems modeling and analysis, and  directly applicable to any complex and multi-agent system. 

I always pursued a central goal in my contributions to projects: turning complex, noisy data into reliable insights that help experts understand systems and provide foresight for better decision-making. 

My expertise spans large-scale data fusion and advanced data science methodologies, including machine and deep learning, Bayesian inference, time-series and state-space modeling, and optimization, combined with traffic flow theory, driving behavior analysis, safety, and risk modeling. I have designed end-to-end analytical pipelines that integrate heterogeneous data sources, ranging from vehicle trajectories, road sensors (loop detectors), LiDAR data,  and video streams to survey and textual data, to extract actionable insights for complex real-world systems such as traffic operations, safety assessment, and decision support. 

Across my career, I have worked on both policy-oriented and research-driven projects, collaborating with universities, public authorities, and industry partners in international settings. I value methodological rigor, interpretability, and reproducibility, and I am particularly interested in applying data-driven approaches to real-world challenges where system behavior, uncertainty, and human decision-making play a central role. My broader goal is to contribute analytical and computational tools that improve safety, efficiency, and sustainability in complex socio-technical systems.