Systems Data Science | Applied AI | Systems Engineering | Operational Analytics
I design and apply analytical, AI-enabled and systems-based approaches to operational problems. My work sits at the intersection of systems engineering, operational analysis, applied data science, optimisation, simulation, and decision-support tooling.
This GitHub profile highlights a selected body of public work and supporting material. It is intended as a professional overview of how I approach technical problem solving: with attention to requirements, workflow, usability, operational context, and measurable outcomes.
This profile serves as a navigation point to my wider portfolio, selected repositories, presentation material, and public technical writing which you can access here:
👉 GitHub Pages portfolio: https://pierswalker71.github.io/
I use the term Systems Data Science to describe the combination of systems thinking, systems engineering and applied data science to develop useful, responsible and operationally effective solutions.
The approach spans problem framing, requirements analysis, workflow understanding, modelling, optimisation, AI tooling, usability, governance, deployment context and evaluation of real-world performance and impact.
In practice, this means treating analytics and AI not as isolated technical capabilities, but as components within wider systems of people, processes, information, technology and governance. The aim is to build solutions that work for real users, fit real workflows, operate under real constraints and deliver meaningful outcomes in practice.
You can read more about my thoughts on this in my paper on Systems Data Science
- AI-enabled decision-support tools and workflow integration
- Applied machine learning and analysis of unstructured data
- Requirements-led analytical system design
- Usability, human-centred workflows and stakeholder adoption
- AI governance, testing, assurance and responsible and ethical deployment
- Operational analytics, modelling, simulation and optimisation
Practical AI systems developed or trialled within organisational workflows, with attention to transparency, testing, compliance and usability.
Selected historical repositories showing technical development across optimisation, simulation, visualisation and machine learning.
My background spans more than two decades across government, consultancy and technical assurance environments. I have worked across modelling and simulation, optimisation, systems engineering, engineering scrutiny, operational analysis, technical risk, AI guidance, AI testing, data science leadership, and analytical decision support.
That experience has shaped a practical view of technical work: the application of data science must be credible, operationally relevant, and usable within the systems and workflows they are meant to support.
This portfolio also includes selected presentation material, conference content, technical notes, and public-facing summaries where appropriate. These provide additional evidence of analytical thinking, communication, and engagement with complex technical subjects.
Some repositories here are older exploratory projects developed during periods of learning, experimentation, and technical development. They are retained as part of an honest record of progression, particularly in simulation, optimisation, machine learning, and analytical prototyping.
They should be read as foundational work rather than as a representation of my current technical practice.