Project catalog
Pipelines, attribution platforms, dashboards and models — each one stating the problem, what I built, and what changed as a result. The four below have full case studies with the evidence behind them.
The Migration
Sole architect of a multi-touch attribution platform unifying Meta Ads, GoHighLevel, GA4 and Google Search Console through native API integration — a Streamlit application that replaced siloed marketing and CRM data with one source of truth.
5,200+ leads and a USD 10K/month media budget tracked end to end. CPL USD 7.45, cost-per-appointment USD 11.58. Adopted by the CEO as the primary strategic decision tool.
The Migration
Nearly a third of booked consultations never happened — and outcome data was too unreliable to see it. I fixed the measurement first, then found the leak and closed it.
Show rate climbed from 68% to 82% — roughly one in five no-shows recovered, from the same bookings and zero extra ad spend.
The Migration
A lead conversion model that scored a suspicious 100%. I audited it, found the leakage, deleted the data that made it perfect, and rebuilt it honestly.
77% accuracy against a 62% baseline. Top-scoring 20% of leads converted at 84%; referral converted at 90% versus 26% for paid social.
The Migration
Full CRM build-out — workflows, automations, pipelines, calendars and platform integrations — with data governance protocols that made GoHighLevel the enterprise single source of truth.
Every lead lifecycle stage captured consistently, which is what made attribution and show-rate measurement possible in the first place.
Shipped and in use, without a long write-up.
The Migration
Per-agent BI dashboard surfacing individual revenue contribution, nurturing velocity and pipeline-to-close conversion rates for the counsellor team.
Used by leadership to run data-driven 1-on-1 performance reviews, replacing subjective assessment with per-agent pipeline evidence.
Sapphire Finishing Mills
Automated extraction, transformation and load pipeline replacing a recurring manual reporting workflow that consumed an hour of analyst time per run.
Compressed a 1-hour analysis cycle to 14 seconds — eliminating transcription errors and reclaiming 4+ team hours per iteration.
Sapphire Finishing Mills
Z-test model that reads a fabric's reprocess history to predict how long it will take to reach dispatch. It returns a day range rather than a false-precision single date, and scores every order against its due date as a probability of packing on time — surfaced as a colour-coded metric across the floor.
Production leadership could see at a glance which orders were on track, at risk, or certain to miss — turning scheduling from reactive firefighting into planning. Delivered a 20% gain in operational planning efficiency.
The Migration
Machine learning model over historical client call audio from the CRM, predicting which clients are most likely to convert. It rates each conversation and surfaces the patterns that separate a call that closes from one that does not.
Turns a subjective "how did that call go?" into a rated, comparable signal — feeding both lead prioritisation and specific coaching points for the sales team.
The Migration
Programmatic synchronisation of quarterly OKRs and daily task execution in ClickUp via custom API integrations, built with Claude Code — closing the loop between analytics outputs and project delivery.
Modernised the Agile framework for a 12-person marketing department.