Abstract / Description of output
We address the problem of obtaining score-based clusters for time-evolving
populations. We consider two objectives: the similarity of the
so-obtained clusters to given reference clusters, and the smoothness of
the clusters along the time horizon, both to be maximized. For particular
cases of relevance, different solutions of the bi-objective problem
are generated in polynomial time and represented, allowing the user to
select an appropriate trade-off between similarity to reference clusters
and clustering smoothness. The methodology is applied to clustering
Higher Education institutions in the United Kingdom tracking the satisfaction
score of the annual National Student Survey.
populations. We consider two objectives: the similarity of the
so-obtained clusters to given reference clusters, and the smoothness of
the clusters along the time horizon, both to be maximized. For particular
cases of relevance, different solutions of the bi-objective problem
are generated in polynomial time and represented, allowing the user to
select an appropriate trade-off between similarity to reference clusters
and clustering smoothness. The methodology is applied to clustering
Higher Education institutions in the United Kingdom tracking the satisfaction
score of the annual National Student Survey.
| Original language | English |
|---|---|
| Pages | 72 |
| Number of pages | 72 |
| Publication status | Published - 2015 |
| Event | 27th European Conference on Operational Research (EURO 2015) - Glasgow, United Kingdom Duration: 12 Jul 2015 → 15 Jul 2015 |
Conference
| Conference | 27th European Conference on Operational Research (EURO 2015) |
|---|---|
| Country/Territory | United Kingdom |
| City | Glasgow |
| Period | 12/07/15 → 15/07/15 |