Exploring and evaluating a multi criteria forecasting decision support system

Applications are invited for a fully-funded three year PhD to commence in October 2021. 

The PhD will be based in the Faculty of Business and Law, and will be supervised by Dr Huijing Chen, Dr Maria Barbati and Professor Salvatore Greco. 

Candidates applying for this project may be eligible to compete for a Portsmouth Global PhD scholarship. Successful candidates will receive a scholarship to cover tuition fees at an international rate for three years, a stipend in line with the UKRI rate (£15,609 for 2021/22), and one return flight to London during the duration of the course. 

The Faculty of Business and Law offers funding to support conference attendances and external training. You will also have the opportunity to apply for a placement support fund. 

Demand forecasting and multi-criteria decision making (MCDM) are well established Operational Research (OR) techniques that are applied in many different areas. Both are useful tools for planning purposes. To date, there is an extensive body of literature on the development of both disciplines separately, but the potential of combining them is an under-researched area.

Forecasting performance is usually measured by some form of accuracy, while organisations often have other measures in mind when making forecasting decisions, such as sales targets, promotional campaigns and sustainability considerations among many others. Only recently, the need for non conventional errors of measure have been proposed in Kück et al., (2021). Although a range of measures have been adopted to evaluate different forecasting methods and the parameters of specific methods, the analysis of the preferred method is relying on a simplistic choice without a more structured investigation of the choice problem. Instead, MCDM techniques could help in defining how the evaluation of forecasting methods and the choice of the parameters can happen, considering a variety of performance measures that can be assumed as the criteria to optimise. MCDM techniques could be particularly useful because they can take into account not only a variety of measures, including qualitative evaluations, but also their interaction and their hierarchy. Moreover, robustness of the forecasting techniques can be enhanced by taking into account  misspecification of the model measured in terms of stability with respect to perturbations of the model parameters in the perspective of some well-known approaches in the domains of economics and decision under uncertainty.

Therefore, there is a strong argument to call for inter-disciplinary research combining forecasting and MCDM techniques, and enhancing understanding of how these two well-established disciplines should be combined to benefit organisational planning decisions. 

References

Kück, M., & Freitag, M. (2021). Forecasting of customer demands for production planning by local k-nearest neighbor models. International Journal of Production Economics, 231, 107837.

How to apply

We’d encourage you to contact Dr Huijing Chen (huijing.chen@port.ac.uk) to discuss your interest before you apply, quoting the project code.

When you are ready to apply, you can use our online application form. Make sure you submit a personal statement, proof of your degrees and grades, details of two referees, proof of your English language proficiency and an up-to-date CV. Our ‘How to Apply’ page offers further guidance on the PhD application process. 

Please also include a research proposal of 1,000 words outlining the main features of your proposed research design – including how it meets the stated objectives, the challenges this project may present, and how the work will build on or challenge existing research in the above field.

If you want to be considered for this funded PhD opportunity you must quote project code O&SM6221021 when applying.