DCRMTA: Deep Causal Representation Learning for Multi-Touch Attribution

Multi-touch attribution (MTA) is essential for estimating the contribution of individual advertising touchpoints to user conversions. While recent studies incorporate causal inference to mitigate confounding bias from user preferences, existing multi-stage deconfounding pipelines exhibit a critical structural flaw: they indiscriminately filter out user influences, which inadvertently discards the genuine causal signals linking user covariates to conversions. To resolve this trade-off, we propose Deep Causal Representation for MTA (DCRMTA), an end-to-end framework that explicitly quantifies and preserves the causal impact of user features. By leveraging structural causal modeling and adaptive counterfactual attention perturbations, DCRMTA distills invariant user representations while actively decoupling them from latent confounding variables. Extensive experiments on real-world industrial datasets demonstrate the efficacy of our approach. DCRMTA effectively improves predictive accuracy yielding up to a 5.2% relative improvement in PR-AUC over strong baselines while providing robust, Shapley-based credit allocations across complex marketing channels.