aiqbench analysis
This research introduces an "auto-targeting" framework that jointly optimizes user and item selection for e-commerce campaigns, addressing a key limitation in existing methods that decouple these decisions. By combining constrained spectral biclustering with multi-armed bandits, the approach achieves superior campaign quality and fairness while offering a scalable bandit-based alternative for very large datasets. The work provides a practical solution for retailers seeking to discover high-affinity groupings directly from interaction data without predefined campaign structures.
Constrained user-item allocation for e-commerce marketing campaigns
arXiv:2606.09623v1 Announce Type: new 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.
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.
Machine Learning (cs.LG)
arXiv:2606.09623 [cs.LG]
(or arXiv:2606.09623v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2606.09623 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 283 words
Related coverage
The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs
arXiv · Jun 9, 2026
The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs
arXiv · Jun 3, 2026
AgenticSwarm: Semantic Perception and Adaptive Task Allocation for Heterogeneous Multi-UAV Missions
arXiv · Sep 21, 2026
SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation
arXiv · Sep 30, 2026