Pricing with bandits in the long tail: The role of competitive monitoring

Israeli, Ayelet, Anderson, Eric
Quantitative Marketing and Economics · Springer Nature · 2026-09-21 · DOI: 10.1007/s11129-026-09314-0

Abstract

Most e-commerce retailers offer a long tail of very low-demand products. Individually, these items may have low sales but collectively they are critical to the overall e-commerce business model. Because of their minimal sales, pricing is a constant challenge. The academic literature has considered price exploration as a primary source of information for price adjustments, but this approach may be insufficient in low demand situations. In this paper, we propose a bandit algorithm for long-tail products that is informed by both monitoring competitor prices and price exploration. In the model, the competitor’s posted price is a noisy signal of a latent demand state that the focal firm must pay to observe, and the monitoring rate is an endogenous choice made each period. Our model is motivated by a unique dataset from a large e-commerce firm that regularly monitors competitor prices. The bandit model simulations and empirical data highlight three core findings: (i) monitoring is selective and rare; (ii) monitoring and price exploration are strategic substitutes; and (iii) monitoring larger competitors is associated with higher revenues.

Read at publisher →

Similar articles