Context-Aware Fragrance Discovery: Balancing Semantic Alignment and Catalogue Coverage Through Stochastic Ranking

Abstract

In this paper, we propose a context-aware fragrance recommendation model, which moves the task beyond static similar scent matching towards situational recommendation, where different perfumes are appropriate for different social environments. In our formulation, a perfume collection is modelled as a dynamic olfactory wardrobe, where each perfume is tailored to specific environmental and social demands. We formalize each perfume through a unified representation which combines contextual suitability and affective signals extracted from user reviews, together with olfactory catalogue data. The proposed model integrates deterministic top-k ranking and stochastic candidate selection to balance relevance and exploration. We assess the performance of the model with complementary evaluation measures covering identity retrieval, ranking quality of success hits, semantic utility and catalogue exploration. The results indicate that while even simple popularity baselines remain highly competitive in raw retrieval precision, our fused context-affective model provides stronger contextual utility than single-feature strategies. Furthermore, our stochastic ranking variant substantially improves catalogue coverage with only a limited loss in retrieval quality.