Scott Campbell

Data Analytics, Business Intelligence, and Automation Systems

I build practical analytics and automation systems for operations teams: dashboards, reporting workflows, request trackers, searchable knowledge tools, and automations that reduce manual follow-up.

  • Power BI
  • SQL
  • Python
  • Power Automate
  • SharePoint
  • FastAPI
  • React
  • dbt
  • Time-series data
Grid Intelligence redesigned dashboard overview
Flagship Project Grid Intelligence: live US and European electricity analytics with API ingestion, time-series modeling, anomaly scoring, forecasting, and dashboard delivery.

Selected Projects

Each project is written as a case study with the problem, system design, data flow, implementation choices, and evidence.

Live Public Project

Manufacturing Intelligence Platform

Production-style factory analytics platform using a seeded synthetic assembly dataset, PostgreSQL star schema, FastAPI endpoints, validation checks, and a Next.js executive dashboard.

Value: turns raw operational logs into an executive health dashboard: 90.3% plant OEE with a defensible path from source records to decisions.

Live demo available. Synthetic-data project with current screenshots, validation evidence, and full source repo.

  • PostgreSQL
  • FastAPI
  • Next.js
  • SQL
  • Validation
Manufacturing Intelligence Platform executive dashboard with OEE, yield, defects, and downtime metrics
Live Public Project

Fair Lending Lab

Hypothesis testing and statistical inference platform on CFPB HMDA mortgage data. Five preregistered hypotheses, parametric and non-parametric and permutation and bootstrap and Bayesian sensitivity validation, BH-FDR and Bonferroni correction, effect sizes with confidence intervals, and explicit causal framing caveats.

Value: turns 210,643 raw HMDA records into a fair-lending screening dashboard where every finding is validated by parametric, non-parametric, and resampling methods and corrected for multiplicity across the test family.

Live demo available. Public-data project with current screenshots, multi-method validation, and explicit limitation framing.

  • FastAPI
  • Next.js
  • SciPy
  • statsmodels
  • Postgres
Fair Lending Lab dashboard with what matters now callout, KPI tiles, and denial rate charts

More projects

Smaller systems, same discipline: live demos, real validation, and full case studies.

Automotive Analyst

Bring-your-own-key text-to-SQL agent with schema grounding, read-only SQL guardrails, and visible query evidence.

  • Text-to-SQL
  • FastAPI
  • AI safety

Water System Risk & Funding Priority Index

Explainable Ohio drinking-water risk screening: 16,339 systems scored transparently, 22/22 validation checks passing.

  • Python
  • GIS
  • Public data

Black Box AI

Aviation-safety analytics over 7,462 NTSB reports: guarded SQL counts and cited narrative retrieval, kept separate and auditable.

  • Retrieval
  • SQL safety
  • Postgres

arXiv Recommender

Hybrid paper recommender on 28,000 OpenAlex CS papers: five algorithms benchmarked with bootstrap CIs, top-10 served in under 100 ms p95.

  • FAISS
  • sentence-transformers
  • Postgres

How I build with AI

Every project here was built with AI in the loop, under a method I can defend: I write the spec and the data contract first, AI drafts against that contract, and nothing ships until the test suite passes and the live validation checks are green.

The full write-up covers the logic model I plan with, how I prompt and why, and the layered checks that prove the data is right.

  • Spec first
  • Tests as the gate
  • Validation built in

About the work

I build analytics and automation systems that make operations easier to understand, easier to track, and easier to improve.

My work focuses on the full path from messy process to usable system: intake, data structure, workflow, reporting, and adoption. A dashboard is only useful when the inputs are trustworthy and the process behind it is something people can actually follow.

This portfolio is written for recruiters, hiring managers, and technical interviewers who want to see how I solve real problems beyond a list of tools. Each case study explains the problem, solution, architecture, tradeoffs, and results.