AI summaryⓘ
The authors study how retailers can best pick which products to promote and which users to target together, since these choices affect each other. They call this combined problem 'auto-targeting' and propose three methods to solve it: one that groups users and items based on shared interests (biclustering), one that improves selections by swapping pairs, and another that tries different options to avoid getting stuck on bad choices (multi-armed bandit). Testing on various datasets, the authors find that biclustering works best for smaller cases, but as data grows very large, the bandit method is more practical. Their work helps create more effective and fair marketing campaigns by matching users and products well.
auto-targetingmarketing campaignsspectral biclusteringuser-item affinity matrixgreedy local searchmulti-armed banditcombinatorial optimizationsimulated annealingcampaign targetingfairness in marketing
Authors
Maja Lindström, Natalija Glisovic, Jan von Pichowski, Tommy Löfstedt, Martin Rosvall
Abstract
When running marketing campaigns, retailers must decide which products to promote and which users to target. These decisions are inherently coupled: effective campaigns match users and items with strong mutual affinity into non-overlapping groups of predefined sizes. However, existing approaches assume predefined campaign structure or decouple item selection from user assignment, and cannot discover campaign groupings directly from joint interaction patterns. We therefore formalize this campaign problem as auto-targeting: jointly selecting users and items to construct multiple disjoint campaigns. To solve this combinatorial problem, we propose three complementary strategies: (i) constrained spectral biclustering to find dense regions in the user-item affinity matrix, (ii) greedy local search with pairwise swaps for combinatorial refinement, and (iii) a multi-armed bandit framework to escape local optima through exploration. We evaluate these methods on a synthetic dataset, the Amazon Reviews benchmarks, and large-scale proprietary commercial data, and compare the results to simulated annealing as a baseline. The results show that biclustering consistently achieves the highest campaign quality, lift, and fairness scores. While biclustering runs efficiently on smaller datasets, its runtime increases substantially on very large ones, where bandit-based methods instead offer a scalable alternative.