arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.06368cs.LGecon.EMmath.OCstat.MEstat.ML
收藏

基于半参数模型的动态定价策略优化

Policy Optimization Using Semi-parametric Models for Dynamic Pricing

Princeton University(普林斯顿大学)

Jianqing Fan, Yongyi Guo, Mengxin Yu

摘要:

在本文中,我们研究的上下文动态定价问题的市场价值是线性的,在其观察到的功能加上一些市场噪音。产品一次销售一个,并且只观察到指示销售成功或失败的二进制响应。我们的模型设置类似于Javanmard和Nazerzadeh [2019],只是我们将需求曲线扩展为半参数模型,并且需要动态学习参数和非参数组件。我们提出了一个动态的统计学习和决策政策,结合半参数估计从广义线性模型与未知的链接和在线决策,以最大限度地减少遗憾(最大限度地提高收入)。在温和的条件下,我们表明,市场噪声c.d.f. $F(\cdot)$与$m$阶导数($m\geq 2$),我们的策略实现了$\tilde{O}_{d}(T^{\frac{2m+1}{4m-1}})$的遗憾上界,其中$T$是时间范围,$\tilde{O}_{d}$是隐藏对数项和特征$d$维数的阶数。如果$F$是超光滑的,其傅里叶变换呈指数衰减,则上界进一步降低到$\tilde{O}_{d}(\sqrt{T})$。就对水平$T$的依赖性而言,这些上限接近$Ω(\sqrt{T})$,即$F$属于参数类的下限。我们进一步推广这些结果的情况下,动态依赖的产品功能的强混合条件。

英文摘要:

In this paper, we study the contextual dynamic pricing problem where the market value of a product is linear in its observed features plus some market noise. Products are sold one at a time, and only a binary response indicating success or failure of a sale is observed. Our model setting is similar to Javanmard and Nazerzadeh [2019] except that we expand the demand curve to a semiparametric model and need to learn dynamically both parametric and nonparametric components. We propose a dynamic statistical learning and decision-making policy that combines semiparametric estimation from a generalized linear model with an unknown link and online decision-making to minimize regret (maximize revenue). Under mild conditions, we show that for a market noise c.d.f. $F(\cdot)$ with $m$-th order derivative ($m\geq 2$), our policy achieves a regret upper bound of $\tilde{O}_{d}(T^{\frac{2m+1}{4m-1}})$, where $T$ is time horizon and $\tilde{O}_{d}$ is the order that hides logarithmic terms and the dimensionality of feature $d$. The upper bound is further reduced to $\tilde{O}_{d}(\sqrt{T})$ if $F$ is super smooth whose Fourier transform decays exponentially. In terms of dependence on the horizon $T$, these upper bounds are close to $Ω(\sqrt{T})$, the lower bound where $F$ belongs to a parametric class. We further generalize these results to the case with dynamically dependent product features under the strong mixing condition.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑