Projects
Field notes from real pipelines and published research, along with the code that ran them.
Professional Work
Building a Real-Time School Climate & Equity Analytics Platform
A production-grade batch and streaming ELT platform investigating whether real-time school climate signals are leading indicators of future social vulnerability — Kafka, Databricks, Snowflake, dbt, and a RAG service that lets district leaders ask equity questions in plain English.
PythonSQLYAMLBashJavaScript
Data EngineeringData AnalysisComplianceDevSecOpsPublic HealthOpen DataETL/ELTRAGEquityCloudResearch
Building a DevSecOps-Ready GCP ETL Pipeline for Multi-Year Google Sheet Survey Analysis
A behind-the-scenes look at engineering a secure, reproducible, analytics-ready GCP ETL pipeline that automates ingestion and transformation of multi-year, multi-language Google Sheet survey data.
BashPythonYAML
Data EngineeringDevSecOpsETL/ELTCloudNonprofit
Querying NYSED School Data in Microsoft Access Using SQL: Graduation, ELA, and Math Insights
How to use SQL in Microsoft Access to query NYSED education data for specific schools — real-world examples of filtering, joining, unions, and ordering datasets.
SQL
Data AnalysisEducationOpen Data
From Chaos to Clarity: A Lightweight Multilanguage ETL Pipeline for Excel ↔ SharePoint Integration
A practical, human-centered data migration framework blending Python, Bash, and JavaScript to automate the transition across SaaS platforms — making complex data accessible, secure, and easy to navigate.
PythonBashJavaScript
Data EngineeringETL/ELTComplianceNonprofit
Why Microsoft VBA Still Matters: Automating Data Workflows in Excel with Visual Basic
Why Microsoft VBA still matters in 2025 — simple Excel macros that automate data workflows, streamline reports, and empower nonprofit and education teams.
VBA
Data AnalysisAutomationNonprofit
Automating NYC InfoHub Data Collection with an Intelligent Excel Web Scraper
How intelligent web scraping, concurrency, and security checks turn NYC InfoHub's sprawling maze of Excel datasets into a fast, verifiable, and human-accessible data repository.
Python
Data EngineeringAutomationWeb ScrapingOpen Data
Regression Analysis for SARS-CoV-2 RNA Concentrations in NYC Wastewater
An analysis of trends in SARS-CoV-2 RNA concentrations in NYC wastewater during the height of the COVID-19 pandemic — API ingestion, SQLite modeling, and regression analysis.
Python
Data ScienceMachine LearningPublic HealthCOVID-19
Student Adaptability Level Classifier in Online Education
Extensive EDA with Python, pandas, and matplotlib, plus supervised ML with scikit-learn — training and evaluating classification models for student adaptability.
Python
Data ScienceMachine LearningEducationEquityCOVID-19
Research
TardyGrad: Benchmarking Biologically Plausible Learning Against Backpropagation
Project TardyGrad benchmarks Node Perturbation, Predictive Coding, and Hebbian Learning against Backpropagation on MNIST — in standard ANNs and Spiking Neural Networks — then tests all three under delayed reward conditions to probe the limits of gradient-free learning.
Python
NeuroAIComputational NeuroscienceMachine LearningData ScienceResearch
Encoding and Decoding Behavioral Signals in Mouse Visual Cortex: A GLM Study Across Learning Stages
Fitting Generalized Linear Models to 50,000+ neuron recordings across V1 and higher visual areas of the mouse visual cortex to decode behavioral variables — lick, reward, cue, velocity, and texture — across supervised and unsupervised learning stages, extending Zhong et al. (Nature, 2025).
Python
Computational NeuroscienceData ScienceResearch
Evaluating authenticity and quality of image captions via sentiment and semantic analyses
How sentiment and semantic variance analyses assess the quality of image captions in large datasets like COCO — examining how human-generated captions reflect meaning.
Python
NLPMachine LearningComputational NeuroscienceResearchComputer VisionData Science