Recommendation under Capacity Constraints
This addresses a common but overlooked scenario in recommender systems where items have finite capacities, impacting users and platforms in domains like POIs and e-commerce, though it is incremental as it builds on existing methods.
The paper tackles the problem of recommending items under capacity constraints, such as limited seats or inventory, by extending three state-of-the-art latent factor methods (PMF, GeoMF, BPR) to optimize for both accuracy and expected item usage that respects these constraints, showing benefits in real-world datasets for item and POI recommendation.
In this paper, we investigate the common scenario where every candidate item for recommendation is characterized by a maximum capacity, i.e., number of seats in a Point-of-Interest (POI) or size of an item's inventory. Despite the prevalence of the task of recommending items under capacity constraints in a variety of settings, to the best of our knowledge, none of the known recommender methods is designed to respect capacity constraints. To close this gap, we extend three state-of-the art latent factor recommendation approaches: probabilistic matrix factorization (PMF), geographical matrix factorization (GeoMF), and bayesian personalized ranking (BPR), to optimize for both recommendation accuracy and expected item usage that respects the capacity constraints. We introduce the useful concepts of user propensity to listen and item capacity. Our experimental results in real-world datasets, both for the domain of item recommendation and POI recommendation, highlight the benefit of our method for the setting of recommendation under capacity constraints.