Hi, I'm John
Bridging the gap between complex data pipelines and executive strategy. I leverage SQL, Python, and advanced BI frameworks to clean large-scale transactional data and build predictive analytics infrastructure.
Bridging the gap between complex data pipelines and executive strategy. I leverage SQL, Python, and advanced BI frameworks to clean large-scale transactional data and build predictive analytics infrastructure.
I am an Advanced Data Analyst and Applied Statistician specializing in transforming large-scale, unstructured data into high-impact business intelligence. My work bridges the gap between complex statistical models and executive-level strategy.
With a focus on the commercial, retail, and financial sectors, my expertise spans the full data analytics lifecycle: engineering public data extraction pipelines, designing robust ETL workflows, modeling customer behavior via unsupervised machine learning, and delivering enterprise-grade interactive dashboards.
Data Quality & Validation
Relational Databases & Data Modeling
Enterprise BI & Dashboards
Automated Data Pipelines (ETL)
I design intelligent mobile surveys using ODK (Open Data Kit) and KoboToolbox, integrating them directly with automated Google Sheets trackers for real-time field monitoring and research analytics.Extract massive public datasets from scratch—whether mining market intelligence or syncing with live APIs to deliver the raw data needed to drive strategy.
Using Python and SQL, I handle deep data engineering.I clean, transform, reshape, and structure complex transactional records into clean, dependable, and highly optimized database schemas built for rapid query execution.
I apply rigorous statistical summaries and correlation checks to uncover the underlying patterns within your historical performance.This bridges the gap between raw numbers and clear, foundational business intelligence
I design high-impact, interactive dashboards using Power BI and Python visualization libraries.I translate complex analytics into dynamic, visual narratives tailored directly for category managers and corporate stakeholders.
I write production-ready code to fully automate your data workflows,establishing scheduled ETL pipelines that run seamlessly in the cloud. This transforms manual work into a repeatable, hands-off system.
I execute large-scale web scraping and sentiment analysis pipelines to track market trends, consumer behavior, and competitive landscapes.
I deploy advanced statistical and machine learning models (such as K-Means clustering and predictive algorithms)to forecast demand, evaluate credit risk, and segment consumer behavior with high precision.
Processed 260K+ transaction records, using text-mining and regex engines to extract structural features and profile consumer cohorts. Developed an algorithmic similarity matching engine leveraging Pearson Correlation (r) and Min-Max Magnitude Distance to establish pre-trial historical baselines. Applied automated two-sample t-tests to evaluate store layout trials, successfully validating net revenue expansion while executing critical diagnostic audits on localized traffic anomalies to protect corporate profit margins.
View Project
Constructed a dynamic, KPI-focused executive reporting suite tracking metrics for an e-commerce operation ($323K+ total sales across 15K+ transactions). Developed advanced, custom DAX measures to calculate rolling averages, year-over-year revenue velocity, and average transaction size bounds. Engineered interactive geospatial heat maps and cohort distribution matrices, giving stakeholders an immediate, scannable overview of regional performance and sales density.
View Project
Exploratory analysis using Seaborn's MPG dataset to uncover trends in retail performance.
View Project
Data cleaning, pivoting, and calculations with dashboard visuals.
View Project
Python KPI-focused reports with role-based access and automated refresh.
View Project