Project: Implementation of inference algorithms for the imprecise Plackett–Luce model
Description
The Plackett–Luce model is a popular parametric probabilistic model to define distributions between rankings of objects, modelling for instance observed preferences of users or ranked performances of algorithms. Since such observations may be scarce (users may provide partial preferences, or not all algorithms are run for a given experiment), the parameters of the Plackett–Luce model may not be precisely known. In a recent paper https://dx.doi.org/10.1016/j.fss.2024.108908 , two inference algorithms have been devised, but they have not been implemented
The aim of this master project is to study the two algorithms in the paper mentioned above, and implement them. Such an implementation would be useful to have, as it allows to do an experimental study of how well the imprecise Plackett–Luce model performs on real datasets. In the second part of this project, the student will perform an experimental study on some datasets.
Literature
Inferring from an imprecise Plackett–Luce model:
https://dx.doi.org/10.1016/j.fss.2024.108908
Details
- Supervisor
-
Arthur van Camp
- Interested?
- Get in contact
- Link
- Thesis