Developed an unsupervised machine learning clustering model using Python and Scikit-learn to identify disconnected communities in San Diego County, pinpointing critical service gaps and guiding strategic community service enhancements.Led the development and data integration of urban planning tools on the SANDAG Open Data Portal, enhancing public decision-making by synthesizing socio-economic, housing, crime, and demographic data.Conducted advanced geospatial analysis using Python and GeoPandas for the 'Employment Centers' project at SANDAG, analyzing commuter patterns to enhance transportation networks and infrastructure development tailored to urban needs.Directed and mentored a team of junior data scientists at SANDAG, focusing on cultivating their technical and collaborative skills through structured mentorship and hands-on project involvement.Actively led and participated in discussions at U.S. Census Bureau workshops (2024), presenting the SANDAG 'Employment Center' project, which involved analyzing commuting patterns in San Diego using socio-economic and transportation data to provide insights into regional workforce dynamics.

Significantly enhanced the Streetlytics pedestrian model at by integrating machine learning algorithms like Random Forest and Neural Networks using Python's Scikit-learn, achieving a 30% improvement in estimating pedestrian volumes across over 50,000 North American road segments.Spearheaded the development of a supervised classification tree model using R, improving vehicle type classification accuracy by 20% by categorizing data from Automatic Traffic Recorders (ATR) into distinct categories like cars, trucks, and buses.

Performed comprehensive data quality checks on large datasets derived from GPS tracking and socio-demographic surveys using SQL and PySpark, identifying key data inconsistencies and patterns to enhance the reliability of the Streetlytics platform.Developed an advanced Rshiny dashboard to analyze web data for sports events, utilizing text analysis and web scraping techniques to enable accurate travel demand forecasts from various online sources.

Taught advanced courses in Data and Systems Analysis at Utah State University, focusing on rigorous statistical and optimization methods, including regression, classification, and linear programming, to address complex analytical problems and enhance system efficiency.

Designed and managed extensive surveys linking socio-economic factors with walking behaviors in doctoral research at Utah State University, developing multiple databases to deeply analyze behavioral and socio-economic correlations.Led a study on pedestrian behavior involving individuals with disabilities (2012-2016), using advanced statistical methods to model walking patterns, contributing significant findings to peer-reviewed publications and international conferences.