Constrained user-item allocation for e-commerce marketing campaigns
Researchers have developed a new method called auto-targeting to optimize e-commerce marketing campaigns by jointly selecting users and products. The approach uses constrained spectral biclustering, greedy local search, and a multi-armed bandit framework to create disjoint campaigns with strong user-item affinities. Evaluations on synthetic and real-world datasets indicate that biclustering yields high-quality, fair campaigns, while bandit methods offer scalability for larger datasets. AI
IMPACT Introduces a novel approach to personalize marketing by jointly optimizing user and item selection for better campaign performance.