Learning to Price: Interpretable Attribute-Level Models for Dynamic Markets
This work addresses the challenge of scalable, interpretable pricing for dynamic markets, offering a solution that combines efficiency with transparency, though it appears incremental by building on low-rank bandit formulations.
The paper tackled the problem of dynamic pricing in high-dimensional markets by introducing an interpretable additive feature decomposition model and an online learning algorithm, achieving a sublinear regret of ˜O(√d T^{3/4}) and demonstrating near-optimal pricing, rapid adaptation, and transparent explanations in synthetic and real-world datasets.
Dynamic pricing in high-dimensional markets poses fundamental challenges of scalability, uncertainty, and interpretability. Existing low-rank bandit formulations learn efficiently but rely on latent features that obscure how individual product attributes influence price. We address this by introducing an interpretable \emph{Additive Feature Decomposition-based Low-Dimensional Demand (\textbf{AFDLD}) model}, where product prices are expressed as the sum of attribute-level contributions and substitution effects are explicitly modeled. Building on this structure, we propose \textbf{ADEPT} (Additive DEcomposition for Pricing with cross-elasticity and Time-adaptive learning)-a projection-free, gradient-free online learning algorithm that operates directly in attribute space and achieves a sublinear regret of $\tilde{\mathcal{O}}(\sqrt{d}T^{3/4})$. Through controlled synthetic studies and real-world datasets, we show that ADEPT (i) learns near-optimal prices under dynamic market conditions, (ii) adapts rapidly to shocks and drifts, and (iii) yields transparent, attribute-level price explanations. The results demonstrate that interpretability and efficiency in autonomous pricing agents can be achieved jointly through structured, attribute-driven representations.