arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2611.06111stat.AP
收藏

当预测拟合产生误导:使用实验性广告支出回报率基准选择营销组合模型

When Predictive Fit Misleads: Selecting Marketing Mix Models Using Experimental RoAS Benchmarks

Measured Inc.(Measured公司);Goizueta Business School, Emory University(埃默里大学戈伊泽塔商学院)

Hao Chen, Alvin Lim

AI总结:

该研究指出营销组合模型的预测拟合指标与RoAS恢复效果存在偏差,提出采用实验性RoAS基准选择模型的工作流程,可提升RoAS估算准确性。

摘要:

营销组合模型(MMMs)用于估算渠道层面的广告支出回报率(RoAS)并指导营销投资,然而通常会基于预测拟合指标(如样本外R平方、平均绝对百分比误差(MAPE)或均方根误差(RMSE))对不同模型设定进行比较。我们表明,预测拟合可能与驱动营销决策的因果量的恢复情况存在偏差。在具有已知RoAS的模拟中,拟合效果最佳的设定往往并非最准确恢复RoAS的设定;重复研究显示,这种不一致具有系统性,且在媒体支出共线性、噪声以及设定错误的滞后效应形状下依然存在。与基于拟合的选择相比,针对实验性RoAS基准(即使是不精确的基准)选择模型设定可改善RoAS的恢复效果,且一项使用实验性基准的实际应用也呈现相同模式。我们提出了一种实用工作流程:当存在与估计量对齐的实验性基准时,据此校准MMM设定;否则,报告合理设定范围内的RoAS敏感性,而非依赖单一拟合最佳的模型。

英文摘要:

Marketing Mix Models (MMMs) are used to estimate channel-level Return on Ad Spend (RoAS) and guide marketing investment, yet competing specifications are usually compared on predictive-fit metrics such as out-of-sample R-squared, MAPE, or RMSE. We show that predictive fit can diverge from recovery of the causal quantities that drive marketing decisions. In simulations with known RoAS, the best-fitting specification is often not the one that recovers RoAS most accurately; replicated studies show that this disagreement is systematic and persists under media-spend collinearity, noise, and a misspecified carryover shape. Selecting specifications against experimental RoAS benchmarks, even imprecise ones, improves RoAS recovery relative to fit-based selection, and a real-world application with experimental benchmarks shows the same pattern. We propose an applied workflow: calibrate MMM specifications against estimand-aligned experimental benchmarks when they exist, and otherwise report RoAS sensitivity across plausible specifications rather than relying on a single best-fitting model.

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。

↑