I build FTE models, inflow forecasts, automated data pipelines, and causal-inference and optimisation studies, informed by day-to-day analysis, reporting, and data validation, that turn messy, real-world problems into repeatable, data-driven decisions. Built with Python, R, SQL, Power BI, Snowflake and dbt.

Jesse O'Brien, Workforce Modelling & Data Specialist based in Auckland, New Zealand

Auckland, New Zealand · remote friendly

5 years in workforce analytics

PL-300 certified

Python · R · SQL · Power BI · Snowflake · dbt

Who is Jesse O'Brien?

A little bit about me.

I build data systems: FTE models, inflow forecasts, and 50+ Power BI dashboards at ACC, New Zealand's national injury insurer, plus independent projects in causal inference, optimisation, and forecasting that run on production infrastructure built to keep working unattended, published in the open with their methods, their limitations, and their mistakes included. My toolkit spans Python, R, SQL, dbt, Snowflake and Power BI.

I'm equally comfortable as a hands-on technical practitioner and as the data SME in the room, translating complex data work into decisions that stakeholders can act on, from planners and real-time analysts through to executive leadership.

I'm also available for contract work through Confidirect.

What I'm Building.

Selected projects.

NYC 311 Demand Intelligence

An end-to-end data platform forecasting NYC 311 service request demand across 6.2M records and 14 complaint categories. A production-style dbt + DuckDB pipeline feeds a hybrid Prophet/LightGBM forecasting model (27.6% mean MAPE) and a Gemini-powered natural language data assistant, all served through a Streamlit dashboard with live staffing recommendations.

PythondbtDuckDBProphetLightGBMStreamlitGemini API

View project

Undercut

F1 pit strategy under safety-car uncertainty: a tyre-degradation and safety-car hazard model feed a CP-SAT solver that commits to a pit plan before knowing if a safety car comes out, then scores it against what actually happened and a perfect-foresight oracle. Across 652 driver-races, the strategy captured 58% of the value hindsight had available. Live solver studio built with FastAPI and React.

PythonOR-ToolsFastAPIReactDockerGitHub Actions

View project

Last Mile

A staggered-adoption causal study (Callaway-Sant'Anna) testing whether a country's internet actually gets faster once Starlink arrives, using Ookla's public speed-test data rather than the marketing. The naive comparison came back negative; correcting for a confounded control group revealed a real but modest effect, a few Mbps rather than the dramatic jump the hype implies.

PythonRDifference-in-DifferencesHonestDiDOokla

View project

View all projects

My experience.

Workforce Modeller

Current

Apr 2026 – Present

  • Act as a key modelling and data SME within a WFM function of 70+ staff, advising planners, real-time analysts, and leadership on technical feasibility, data interpretation, and process capability.
  • Build FTE scenario models for new business initiatives, quantifying workforce impact of moving work between teams, standing up new functions, or absorbing inflow changes at scale.
  • Develop what-if and transition models mapping how changes in one area of the business propagate FTE requirements across the wider organisation.
  • Led the end-to-end data modelling and allocation framework design for new workforce functions, from initial scoping through to operationalisation and steady state.

Reporting Analyst

Jul 2025 – Apr 2026

  • Designed, developed and maintained 50+ Power BI dashboards, Streamlit applications, and Excel reports supporting WFM operations, planning, and performance reporting up to executive level.
  • Extracted, cleaned and modelled workforce data from Snowflake, Salesforce, and SQL sources using Python and dbt, ensuring accuracy and timely delivery across WFM reporting cycles.
  • Advised reporting analysts across WFM on data interpretation, query design, and what is achievable within ACC infrastructure constraints.

Workforce Planner

Jul 2024 – Jul 2025

  • Built volume forecasting models using Prophet and LightGBM to predict incoming work inflow across departments, providing the demand signal foundation for FTE planning and capacity modelling.
  • Designed and built WFM forecasting pipelines and department-level inflow models from the ground up, replacing ad-hoc manual processes with automated, reproducible workflows in dbt, Snowflake, and Python.

Earlier at ACC

Operations Analyst

Aug 2023 – Jun 2024

  • Built Python automation scripts that eliminated manual stakeholder processes and directly reduced the need for unplanned overtime, delivering measurable cost avoidance for the business.

WFM Real Time Analyst

May 2022 – Aug 2023

  • Monitored real-time workforce activity across multiple business units within a 250+ FTE operation, managing intraday staffing decisions to maintain service levels.

What I Work With.

My skills & credentials.

Workforce Modelling

FTE modelling Capacity planning Scenario analysis Inflow forecasting Transition modelling Allocation design

Languages

Python pandas Prophet LightGBM scikit-learn SQL DAX M / Power Query VBA Jinja

Data Platform

Snowflake dbt GitHub Actions Azure Pipelines Git

Visualisation

Power BI (PL-300) Streamlit Excel PowerPoint

Automation

Python scripting Power Automate Selenium

Tools

Genesys Cloud Salesforce CRM Emite Microsoft 365

Certifications

Power BI Data Analyst Associate (PL-300)

Microsoft

2023

IBM Data Analyst Professional Certificate

IBM / Coursera

2025

Google Data Analytics Professional Certificate

Google / Coursera

2022

Google Project Management Professional Certificate

Google / Coursera

2025

Lean Six Sigma: White Belt

2024

Education

Bachelor of Business Administration, Project Management & Information Systems

University of Maine at Presque Isle

Let's connect.

Always happy to talk data, modelling, or forecasting. Drop me a line.

[email protected]
Auckland, New Zealand
Resume

© 2026 Jesse O'Brien.