# Optimal Exploration of New Products under Assortment Decisions

arXiv: https://arxiv.org/abs/2604.18800 · HTML: https://mlsanity.com/paper/2604.18800/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 51 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 6 of 6)

- [Improved Online Confidence Bounds for Multinomial Logistic Bandits](https://mlsanity.com/paper/2502.10020/) (2025)
- [Fair Assortment Planning](https://mlsanity.com/paper/2208.07341/) (2022)
- [VCG Mechanism Design with Unknown Agent Values under Stochastic Bandit Feedback](https://mlsanity.com/paper/2004.08924/) (2020)
- [Learning an Optimal Assortment Policy under Observational Data](https://mlsanity.com/paper/2502.06777/) (2025)
- [Assortment Optimization under the Multinomial Logit Model with Covering Constraints](https://mlsanity.com/paper/2411.10310/) (2024)
- [Social Learning with Limited Attention: Negative Reviews Persist under Newest First](https://mlsanity.com/paper/2406.06929/) (2024)

## Abstract (arXiv)

We study online learning for new products on a platform that makes capacity-constrained assortment decisions on which products to offer. For a newly listed product, its quality is initially unknown, and quality information propagates through social learning: when a customer purchases a new product and leaves a review, its quality is revealed to both the platform and future customers. Since reviews require purchases, the platform must feature new products in the assortment ("explore") to generate reviews to learn about new products. Such exploration is costly because customer demand for new products is lower than for incumbent products. We characterize the optimal assortments for exploration to minimize regret, addressing two questions. (1) Should the platform offer a new product alone or alongside incumbent products? The former maximizes the purchase probability of the new product but yields lower short-term revenue. Despite the lower purchase probability, we show it is always optimal to pair the new product with the top incumbent products. (2) With multiple new products, should the platform explore them simultaneously or one at a time? We show that the optimal number of new products to explore simultaneously has a simple threshold structure: it increases with the "potential" of the new products and, surprisingly, does not depend on their individual purchase probabilities. We also show that two canonical bandit algorithms, UCB and Thompson Sampling, both fail in this setting for opposite reasons: UCB over-explores while Thompson Sampling under-explores. Our results provide structural insights on how platforms should learn about new products through assortment decisions.