Study level

  • PhD
  • Master of Philosophy

Faculty/School

Faculty of Science

School of Mathematical Sciences

Topic status

We're looking for students to study this topic.

Research centre

Supervisors

Dr Mahdi Abolghasemi
Position
Senior Lecturer in Statistical Data Science
Division / Faculty
Faculty of Science

Overview

This PhD project will focus on developing and evaluating multi-objective optimisation models that simultaneously optimise forecasting accuracy and operational decisions in complex systems.

Research activities

Key activities include:

  • comprehensive literature review, upgrading knowledge
  • survey existing methods in forecast-based optimisation, decision-centric forecasting, and multi-objective optimisation
  • formulate novel optimisation models integrating forecast generation (e.g. probabilistic, hierarchical, or physics-informed forecasts) with downstream decisions (e.g. inventory control, load balancing)
  • implement and benchmark evolutionary algorithms, Pareto optimisation, or gradient-based methods for solving these models
  • apply the models in one or two domains:
    • supply chains (e.g. inventory planning, demand forecasting)
    • energy systems (e.g. load forecasting, renewable energy scheduling)
  • explore trade-offs between objectives such as forecast accuracy (e.g. MASE, CRPS) and decision quality (e.g. cost, service level, energy efficiency).

Outcomes

  • Development of new multi-objective optimisation models for forecast-decision integration.
  • At least two high-quality journal publications in forecasting, operations research, or energy systems.
  • Open-source code and reproducible benchmarks for academic and industry use.
  • Practical impact in industry applications, through partnerships with supply chain or energy companies.

Skills and experience

  • A strong background in optimisation, mathematical modeling, and/or forecasting.
  • Degree(s) in industrial engineering, electrical engineering, operations research, or a related quantitative field.
  • Proficiency in programming (e.g. Python, MATLAB, Julia) and experience with optimisation libraries or forecasting packages.
  • Understanding of time series analysis and decision science is highly desirable but not manadatory.
  • Excellent communication and writing skills for research dissemination and collaboration.

Scholarships

You may be eligible to apply for a research scholarship.

Explore our research scholarships

Keywords

Contact

Contact the supervisor for more information.