Project Portfolio & Impact Record

2025-2026

This document provides comprehensive evidence supporting competency across craft skills through 18+ delivered projects spanning CFC Operations, Supply Chain, Last Mile, and ECOM domains. Includes internal platforms (Analyticado, K-AI), operational analytics (Cost to Serve, Water Limit, Routes Predictor), partner-facing reporting (OSP Insights), and personal product work (Capture).

Get in touch

Core skills

Technical and analytical skills demonstrated across the portfolio.

SQL & Data WarehousingPythonLooker / BI & VisualisationData Analysis & InsightsMachine LearningSoftware EngineeringGCP & CloudData ModellingDashboard DesignStakeholder Communication

Key Impact Highlights

Financial Impact

  • Cost to Serve (Client): ~$1M/year
  • Water Analysis - Geo Cubing: ~$550K/year saved
  • Water Capping Recommendations: ~$300K-~$2M/year potential

Code Contribution

  • Total Lines Written: ~200k lines
  • Internal Looker (LookML): ~125k lines, ~750 commits (#1)
  • External Looker (OSP Insights): ~45k lines, ~75 commits (#5)
  • Python Framework: ~20k lines
  • Analyticado: ~6.5k lines

Platform Reach & Usage

  • Partners Supported: multiple partners
  • Sites Supported: >100 (CFCs, MFCs, in-store)
  • OSP Insights Report Runs: ~3k/month
  • Top Report (In the Bag): ~2k runs/month
  • Analyticado DAU: ~500 users/day

Enablement & Automation

  • Users Trained on Looker: ~100 users
  • OSP Insights Usage: 2x month-over-month
  • GCP Cloud Functions: ~5 in production

International Secondment - Senior Analyst

Cincinnati, Ohio, USA

~15 months (2025-2026)

Completed a ~15-month international secondment to support a strategic partner, working on-site to drive operational efficiency, cost reduction, and performance improvements across a complex end-to-end fulfilment solution.

Impact & Contributions

  • Worked directly with operations leadership, internal analytics teams, and supply chain/logistics teams
  • Provided expertise across supply chain, e-commerce operations, warehouse automation, and inbound/outbound logistics
  • Built and deployed operational reporting; led analytical investigations into performance issues
  • Conducted audits and troubleshooting across systems and processes
  • Mentored partner team members on reporting tools, data interpretation, and building their own solutions
  • Delivered hands-on training and acted as a trusted advisor within the partner organisation
  • Delivered $2M in traceable cost savings (Cost to Serve, Water Limit Analysis)
  • Led multiple analytical workstreams, translating complex data into clear recommendations

Tools & Technologies

Looker / LookML, SQL, React.js, Google Workspace, Google Apps Script

Domain Coverage

CFC Operations: Cost to Serve, TPO Prediction, Workload Forecasting, Pick EAPSupply Chain: Decant EAP, Workload ForecastingLast Mile: Availability Breakdown, Routes Predictor, GeomappingECOM/Customer: Slot Planning, Availability Analysis

Projects at a Glance

Analyticado

Centralised analytics hub with ~500 daily active users

Internal website integrating Looker Enterprise metrics and external analytics outputs. Custom search engine, Looker API integration, embedded dashboards, and UX-focused design. Boosted analytics engagement 10x.

self

Extended write-up

Built and launched Analyticado as the centralised analytics hub for the organisation, integrating Looker Enterprise metrics and external analytics outputs into a single discovery platform. Designed a custom search engine with Looker API integration, embedded dashboards, and UX-focused design. The platform achieved 10x increase in analytics engagement with ~500 daily active users, becoming the one-stop solution for discovering dashboards, reports, and analytical resources. Used storytelling and UX clarity to help stakeholders understand and adopt analytical content. Designed interactive visual interfaces with layout, hierarchy, and typography to enhance usability. Built ingestion and transformation processes pulling Looker metadata, curated sheets, and analytics events. Applied code management and CI/CD principles. Designed normalised BigQuery tables with proper entity separation and 3NF principles. Ensured metadata usage aligned with privacy rules and internal content policies.

Key Impact

  • ~500 daily active users
  • 10x increase in analytics engagement
  • One-stop search for all analytics resources

Technologies & skills

Next.jsReactLooker APITypeScriptBigQuery
Next.jsReactLooker APITypeScriptBigQuery

K-AI - Conversational Analytics Assistant

AI-powered analytics discovery across dashboards, docs, and Slack

Internal AI assistant enabling stakeholders to discover and understand data, dashboards, and documentation using natural language. Reduces friction in analytics discovery and enables non-technical users to query complex data ecosystems. Built with Vertex AI and hybrid search.

self

Extended write-up

Designed and developed K-AI as an internal AI-powered assistant to enable stakeholders to quickly discover and understand data, dashboards, and documentation across the organisation. Built using Vertex AI (Gemini 2.5 Flash) for conversational responses with hybrid search (vector + keyword) integrating Looker metadata, GCS documentation, and Slack channel extractions. Implemented end-to-end pipeline: data ingestion, embedding generation and vector storage, context building and ranking, AI response generation with source citations. Designed BigQuery-backed storage for chat history and user preferences. Built interactive chat interface integrated into internal platform homepage with content filtering, personalised prompts, and source citation system. Reduced friction in accessing analytics and knowledge; enabled non-technical users to query complex data ecosystems using natural language.

Key Impact

  • Reduced friction in accessing analytics and knowledge
  • Enabled non-technical users to query complex data ecosystems
  • Centralised fragmented knowledge into a single interface

Technologies & skills

Vertex AILanceDBReciprocal Rank FusionBigQueryGCPLooker API
Vertex AILanceDBReciprocal Rank FusionBigQueryGCPLooker API

Python Framework

Shared analytics automation platform with ~10 contributors

Reusable Python framework automating data pipelines across Looker, Slack, BigQuery, and email. ML utilities, GCP Cloud Functions, CI/CD via GitLab. Secure credential management and pipeline orchestration.

self

Extended write-up

Created a reusable Python framework automating data pipelines across Looker, Slack, BigQuery, and email. The framework grew to ~20k lines with ~10 contributors and ~5 GCP Cloud Functions in production. Coordinated ingestion, cleaning, and distribution of data using Python and Shell for workflow orchestration. Applied cloud engineering principles (GCP, APIs, GitLab CI/CD) and leveraged fundamental data structures across utility modules. Used scikit-learn and custom ML utilities for common analytical tasks. Managed model execution and error alerting via automated pipelines with monitoring and replacement mechanisms. Used GCP Secrets for credential management; implemented pipeline failsafes reporting failures to Slack. Built 'data fresh as of' tags and validation checks for live reporting. Designed staging and landing tables with normalised structures and separated lookup/reference data into distinct tables.

Key Impact

  • ~20k lines of code
  • ~10 contributors across the team
  • ~5 GCP Cloud Functions in production

Technologies & skills

PythonGCPBigQuerySlack APIGitLab CI/CD
PythonGCPBigQuerySlack APIGitLab CI/CD

Cost to Serve Model

~$1M annual savings through operational optimisation

Analytical model identifying cost inefficiencies in the client's fulfilment operations. Delivered actionable recommendations leading to significant annual savings and a client-facing self-service version.

self

Extended write-up

Developed the Cost to Serve analytical model identifying cost inefficiencies in the client's fulfilment operations. Delivered actionable recommendations that led to ~$1M in annual savings. Built a client-facing self-service version adopted across operations leadership. Used optimisation methods and SQL to model cost drivers; applied data analysis to identify root causes. Ensured data governance and clear storytelling to stakeholders. The model became a core reference for operational cost decisions.

Key Impact

  • ~$1M annual savings for the client
  • Client self-service capability
  • Model adopted across operations leadership

Technologies & skills

SQLBigQueryLookerGoogle Sheets
SQLBigQueryLookerGoogle Sheets

Water Limit Analysis

~$550K saved with ~$2M+ further potential

Geo-cubing analysis of water distribution limits across the client's fulfilment network. Identified optimisation opportunities in capping and routing adopted by operations teams.

stakeholder

Extended write-up

Conducted geo-cubing analysis of water distribution limits across the client's fulfilment network. Identified optimisation opportunities in capping and routing that were adopted by operations teams. Achieved ~$550K/year in direct savings with further recommendations worth ~$300K-~$2M/year. Used applied maths and statistical analysis for geo-spatial modelling. Built SQL queries and Python analysis; communicated findings to client leadership. Demonstrated advanced domain understanding of fulfilment network constraints.

Key Impact

  • ~$550K/year in direct savings
  • ~$300K-~$2M/year in recommended optimisations
  • Adopted by operations leadership

Technologies & skills

SQLPythonBigQueryStatistical Analysis
SQLPythonBigQueryStatistical Analysis

Routes Predictor

ML-powered route forecasting for labour planning

ARIMA-based forecasting model predicting delivery routes. Integrated with GCP Cloud Functions for automated execution. More accurate interim predictions than existing heuristics.

stakeholder

Extended write-up

Built ARIMA-based forecasting model predicting delivery routes to support labour planning. Integrated with GCP Cloud Functions for automated execution and AppScript for stakeholder access. Delivered more accurate interim predictions than existing heuristics, guiding the client toward data-driven labour planning. Used training, tuning, and hyperparameter principles for time series models. Interpreted multivariable patterns (orders, TPO, correlating metrics). Automated forecasting via GCP functions; integrated CSV/JSON ingestion in the pipeline. Guided stakeholders by demonstrating model accuracy and designing reusable, partner-agnostic components.

Key Impact

  • More accurate interim predictions
  • Automated forecasting via GCP pipeline
  • Guided data-driven labour planning for the client

Technologies & skills

Pythonscikit-learnARIMAGCP Cloud Functions
Pythonscikit-learnARIMAGCP Cloud Functions

OSP Insights Platform

Partner reporting with ~3k monthly report runs

Redesigned landing pages and navigation for the partner-facing Looker platform. Structured visual flows across multiple partners and 100+ sites. Produced the most used and impactful reports.

self

Extended write-up

Redesigned landing pages and navigation for the partner-facing Looker reporting platform. Structured visual flows to guide users from summary to detail-level insights across multiple partners and 100+ sites. Achieved 2x month-over-month usage increase. Produced the most used and impactful reports on the platform; top report (In the Bag) logging ~2k runs per month. Designed structured visual flows making anomalies, patterns, and trends more obvious. Used storytelling principles to communicate report structure and purpose. Identified which metrics and dashboards needed prominence based on user behaviour. Worked within LookML's structural constraints, demonstrating understanding of explores and data relationships.

Key Impact

  • 2x month-over-month usage increase
  • ~3k report runs per month
  • Top report ~2k runs/month (In the Bag)

Technologies & skills

LookMLLookerSQLBigQuery
LookMLLookerSQLBigQuery

Capture - Mobile Application

Cross-platform photo sharing app on iOS & Android

Independently designed, developed, and launched a consumer mobile application focused on delayed-reveal photo sharing. Full lifecycle from concept and branding through monetisation and App Store Optimisation.

self

Extended write-up

Independently designed, developed, and launched a cross-platform mobile application (Flutter/Dart) focused on delayed-reveal photo sharing. Full lifecycle ownership from concept and branding through monetisation and App Store Optimisation. Built backend with Supabase (PostgreSQL, Auth, Storage, RLS); integrated Firebase Cloud Messaging, in-app purchases, and Google Mobile Ads. Designed all UI/UX in Figma. Demonstrated end-to-end product ownership, software engineering, and storytelling (go-to-market, ASO). Applied data modelling for user flows and subscription logic. Launched January 2026 with ~100 downloads and ongoing growth.

Key Impact

  • Launched on both app stores (January 2026)
  • ~100 downloads with ongoing growth
  • Full monetisation: subscriptions, one-time purchases, ads

Technologies & skills

FlutterDartSupabasePostgreSQLFirebaseFigma
FlutterDartSupabasePostgreSQLFirebaseFigma

Workload Forecasting ML Models

Network-wide staffing optimisation across 100+ sites

Machine learning models for predicting warehouse workload and staffing needs across the global fulfilment network. Enables proactive resource allocation and labour management.

stakeholder

Extended write-up

Developed machine learning models for predicting warehouse workload and staffing needs across the global fulfilment network. Enabled proactive resource allocation and labour management. Deployed across 100+ sites serving ~10 partner organisations. Built reusable scripts for model execution; integrated with Python framework for automated pipelines. Used scikit-learn and time series techniques. Demonstrated ML Ops practices: monitoring, error alerting, and model replacement mechanisms.

Key Impact

  • Network-wide staffing optimisation
  • Deployed across 100+ sites
  • Serving ~10 partner organisations

Technologies & skills

Pythonscikit-learnBigQueryGCP
Pythonscikit-learnBigQueryGCP

Availability Breakdown

Secured client trust for Auto Route Release

Validated availability behaviour with evidence; exposed gaps in demand capture. Explained complex availability concepts to executives. Built visual tools highlighting patterns and zone-sizing issues.

stakeholder

Extended write-up

Validated availability behaviour with evidence, challenging assumptions and revealing that planners weren't capturing demand as effectively as assumed. Secured client trust for Auto Route Release. Demonstrated advanced domain understanding by explaining complex availability concepts (route release, slot planning, zone configuration) to executives. Used synthesis techniques to turn millions of data points into digestible insights. Performed diagnostic analysis to identify root causes of availability failures. Built optimised SQL queries across operational tables. Created visual tools highlighting patterns, anomalies, and zone-sizing issues. Automated reporting workflows using AppScript. Ensured the tool adhered to privacy, accuracy, and data integrity.

Key Impact

  • Secured client trust for Auto Route Release
  • Revealed zone-sizing and demand-capture issues

Technologies & skills

SQLLookerAppScript
SQLLookerAppScript

In the Bag

Enabled tighter labour management

Live order breakdown and labour demand visibility. Structured insights around stakeholder questions. Real-time performance monitoring for operational decisions.

stakeholder

Extended write-up

Built live order breakdown and labour demand visibility for partner and internal stakeholders. Enabled tighter labour management through real-time performance monitoring. Used domain expertise to align order breakdown logic with operational decision-making. Identified underlying drivers of live order values and labour demand. Wrote efficient SQL queries to extract live and historic values at scale with quality checks. Created visualisations simplifying real-time performance monitoring. Used descriptive analysis (patterns, correlations, temporal structures). Automated data refreshes and workflows using AppScript.

Key Impact

  • Enabled tighter labour management
  • Real-time performance visibility for partners

Technologies & skills

SQLLookerAppScript
SQLLookerAppScript

Geomapping Availability

Exposed zone-sizing and planning issues

Interactive map-based visualisations for availability patterns and zone issues. Dynamic filtering across time, sites, and slot planning areas. Uncovered operational flaws including oversized zones.

self

Extended write-up

Identified a critical visibility gap and designed interactive map-based visualisations for availability patterns and zone issues. Exposed zone-sizing problems and informed route-release and slot-planning improvements. Created dynamic filtering across time periods, sites, and slot planning areas. Synthesised availability data to uncover operational flaws including oversized zones and same-day offering gaps. Identified patterns such as sudden availability drops during peak periods. Built scalable solutions from initial Colab scripts to dynamic, multi-partner tools. Structured data to support spatial relationships and zone analysis.

Key Impact

  • Exposed zone-sizing issues
  • Informed route-release and slot-planning improvements

Technologies & skills

SQLPythonGoogle ColabLooker
SQLPythonGoogle ColabLooker

Craft Competencies Reference

Competencies used to validate project delivery and impact across the portfolio.

Data Pipeline

BI & Visualisation

Data Modeling

SQL & Databases

Data Analysis & Insights

Storytelling with data & Domain Knowledge

Software Engineering

Machine Learning / Applied Maths / ML Ops

Data Governance

Optimisation Methods