A decision support tool for the student-supervisor allocation problem of postgraduate programs

Abstract

The stable supervisor-student allocation (SSA) is crucial in the success of the research at the postgraduate education. The difference of SSA from the well-known student-project allocation (SPA) problem is that it moves the determination of the research topic to after the allocation, thus allowing the student and the lecturer to discuss the research topic. In the education systems of developing countries where decision support systems are not prevalent, the student-lecturer allocation is performed manually with a greedy approach, which can result in unstable matches. In this study, we propose a multi-objective binary model that allows decision-makers to shift between three main allocation strategies with a trade-off parameter. We test the model with a real dataset of a postgraduate program in Turkey. Experiments show that the model can successfully implement different strategies, and there can also be more than one breaking point between strategies. Also, we transform the model into a decision support tool that provides easy use to the decision-maker and reports the solutions of the trade-off parameter sensitivity analysis. The tool reports the level of satisfaction for each strategy at different breakpoints, allowing the decision-maker to see its options.