Causal method finds marketing skills that boost ai ad success
Causal Value Attribution of Marketing Labels in LLM-Generated Ads: A Deconfounder Approach
Artificial IntelligenceComputers and Society
Summary
Figuring out which skills make AI-generated ads better is tricky because many factors can mix together. The authors created a new method called D-VAE to untangle these factors and find which expert labels really help ad performance. They tried it on cosmetic ads and showed it works better than other methods. When tested in the real world, their recommended settings made people engage with ads much more, almost like human experts. This approach helps companies figure out how to value and improve the human skills behind AI-generated content.
What this means in practice
- •For digital marketing teams: Identify which expert labeling strategies causally increase engagement in AI-generated advertisements to optimize marketing campaigns.
- •For advertising platform engineers: Integrate causal attribution methods to improve AI-driven ad creation workflows by valuing and recommending expert input configurations.$Commercial implications: Enables delivery of better-performing ad generation tools that can be sold to marketers seeking higher engagement through AI.
Tested on one dataset.
Authors
Danhong You, Wei Jiang, Zhiqiang, Zheng
Abstract
As AI-generated content becomes commoditized, economic value increasingly shifts from final artifacts to the upstream expertise used to specify inputs that steer LLM generation. Yet organizations lack methods for valuing this expertise and identifying which individual skills or configurations causally improve performance. This study examines generative marketing, where structured expert labels serve as skill primitives conditioning LLM-generated advertisements. Estimating their causal effects is difficult because outcomes reflect stochastic LLM mediation, high-dimensional label interactions, and multimodal confounding. This study proposes D-VAE (Deconfounder Variational Autoencoder), a counterfactual-inference framework integrating a multi-treatment deconfounder with causal representation learning. D-VAE recovers causally disentangled expert-labeling logic and derives PAC-based bounds on omitted-variable bias from single-treatment confounders. Applied to 29,177 foundation-makeup ad creatives, D-VAE outperforms state-of-the-art benchmarks. A field experiment shows that recommended configurations increase engagement by 32.7% and perform statistically indistinguishably from human experts, while a simulation study confirms causal attribution under complex confounding and treatment interactions. Overall, the study shifts value assessment from AI-generated products to skills, providing a foundation for pricing and optimizing AI-augmented skill portfolios.