Overview

I work as a Data Scientist, Decision Scientist, and Optimisation Specialist, building end-to-end decision systems that translate data, models, and uncertainty into actionable plans—across manufacturing, energy, and mining contexts. My industry focus is not “models in isolation”, but deployable decision workflows that fit real operational constraints (data limitations, capacity bottlenecks, lead times, and cross-functional dependencies).

Industry Experience

1) AI & Data-Driven Infrastructure Systems (UTS / Research)

-Designed machine learning and optimisation models for complex engineering systems under uncertainty -Developed data-driven frameworks for system performance analysis and decision-making -Applied predictive modelling techniques to large-scale infrastructure and networked systems -Translated theoretical models into practical, real-world engineering applications

2) Predictive Analytics & System Monitoring

-Developed analytical models to identify patterns, anomalies, and system behaviours in complex datasets -Applied statistical learning and AI techniques for predictive insights and system diagnostics -Experience with time-dependent data and dynamic system modelling -Built frameworks applicable to predictive maintenance and defect detection

3) Applied Industry Research — Energy & Mining Decision Support

Focus: Applied research projects supporting operational decision-making in energy and mining (Australia) What I deliver (industry-facing outcomes):

  • Turning operational and production data into decision support models for planning, prioritisation, and trade-off evaluation.
  • Developing optimisation studies and analytical prototypes with stakeholders, focusing on practicality and operational relevance.
  • Building frameworks that integrate predictive analytics + optimisation for decisions under uncertainty.

Capability Stack (How I Deliver in Industry)

A) Optimisation-Driven Decision Making

I build prescriptive systems for decisions involving competing objectives and real constraints, including:

  • Resource allocation and scheduling under limited capacity
  • Planning under uncertainty and operational risk
  • Multi-objective trade-offs (cost, performance, reliability, feasibility)
  • Constraint-handling when data is noisy, incomplete, or operational rules are complex

B) Machine Learning & Predictive Analytics (Deployment-Oriented)

My ML work is designed to serve downstream decisions, not just accuracy:

  • Forecasting and predictive modelling to inform planning actions
  • Feature engineering and representation learning for decision relevance
  • Robust validation under real-world data limitations
  • Explainability and stakeholder-ready reporting

C) Integrated ML–Optimisation Systems (End-to-End Delivery)

A defining feature of my industry approach is integration:

  • ML models generate forecasts / risk estimates / latent signals
  • Optimisation consumes these signals to recommend feasible actions
  • Outputs are stress-tested via scenarios and constraints
  • Results are communicated through interpretable summaries and decision dashboards

How I Work (Practical Delivery Style)

  • Decision-centric design (start from what must be decided, not from the model)
  • Feasibility-first modelling (plans must work in real constraints)
  • Scenario-aware analysis (plan robustness matters more than idealised optimality)
  • Clear communication (assumptions, limitations, and trade-offs are explicit)
  • Strong background in machine learning and data-driven modelling for engineering systems
  • Experience developing predictive and optimisation frameworks applicable to infrastructure health monitoring
  • Familiar with time-series analysis and system behaviour modelling
  • Capable of designing algorithmic solutions for defect detection and system reliability
  • Experience contributing to digital representations of complex systems (digital twin concepts)
  • Ability to translate research into practical monitoring and decision-support tools