Abstrakt
The main focus of our work is the problem of multiple objectives optimization (MOO) while providing a final list of recommendations to the user. Currently, system designers can tune MOO by setting importance of individual objectives, usually in some kind of weighted average setting.
However, this does not have to translate into the presence of such objectives in the final results. In contrast, in our work we would like to allow system designers or end-users to directly quantify the required relative ratios of individual objectives in the resulting recommendations, e.g., the final results should have 60% relevance, 30% diversity and 10% novelty.
If individual objectives are transformed to represent quality on the same scale, these result conditioning expressions may greatly contribute towards recommendations tuneability and explainability as well as user's control over recommendations. To achieve this task, we propose an iterative algorithm inspired by the mandates allocation problem in public elections.
The algorithm is applicable as long as per-item marginal gains of individual objectives can be calculated. Effectiveness of the algorithm is evaluated on several settings of relevance-novelty-diversity optimization problem.
Furthermore, we also outline several options to scale individual objectives to represent similar value for the user.