Study level

  • PhD
  • Master of Philosophy
  • Honours

Faculty/School

Faculty of Science

School of Mathematical Sciences

Topic status

We're looking for students to study this topic.

Research centre

Centre for Data Science

Energy Transition Centre

Supervisors

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

Overview

This project aims to develop forecasting models that balance accuracy with stability, minimising unnecessary changes in predictions that can disrupt operational decisions.

Research activities

As part of this research, you will:

  • explore quantitative metrics for forecast stability/volatility and nervousness, inspired by decision sciences and forecasting literature
  • extend traditional and machine learning-based forecasting models to penalize excessive variation across forecast updates
  • embed decision implications directly into the forecasting loss function
  • apply and test the models in real-world settings, including:
    • energy demand planning
    • inventory control
    • financial forecasting.

Outcomes

  • Novel models and algorithms that explicitly control forecast volatility.
  • Tools and metrics to evaluate forecast stability alongside accuracy.
  • Publications in top journals in forecasting and applied statistics.
  • Case studies demonstrating improved decision performance in volatile environments.

Skills and experience

  • Strong foundation in statistics, time series forecasting, and applied mathematics.
  • Proficiency in programming (Python or R) and statistical computing.
  • Familiarity with decision theory or operations research is a plus.

Scholarships

You may be eligible to apply for a research scholarship.

Explore our research scholarships

Keywords

Contact

Contact the supervisor for more information.