# DCRMTA: Deep Causal Representation Learning for Multi-Touch Attribution

arXiv: https://arxiv.org/abs/2401.08875 · HTML: https://mlsanity.com/paper/2401.08875/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 16 Jan 2024.

## Builds on (most cited first, 10 of 10)

- [Deep Interest Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1706.06978/) (2017)
- [Causal inference using invariant prediction: identification and confidence intervals](https://mlsanity.com/paper/1501.01332/) (2015)
- [Representation Learning via Invariant Causal Mechanisms](https://mlsanity.com/paper/2010.07922/) (2020)
- [Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations](https://mlsanity.com/paper/2002.04083/) (2020)
- [Display Advertising with Real-Time Bidding (RTB) and Behavioural Targeting](https://mlsanity.com/paper/1610.03013/) (2016)
- [Deep Neural Net with Attention for Multi-channel Multi-touch Attribution](https://mlsanity.com/paper/1809.02230/) (2018)
- [CAMTA: Causal Attention Model for Multi-touch Attribution](https://mlsanity.com/paper/2012.11403/) (2020)
- [CausalMTA: Eliminating the User Confounding Bias for Causal Multi-touch Attribution](https://mlsanity.com/paper/2201.00689/) (2021)
- [Learning Multi-touch Conversion Attribution with Dual-attention Mechanisms for Online Advertising](https://mlsanity.com/paper/1808.03737/) (2018)
- [Interpretable Deep Learning Model for Online Multi-touch Attribution](https://mlsanity.com/paper/2004.00384/) (2020)

## Built on by (most cited first, 1 of 1)

- [Conversion rate prediction in online advertising: modeling techniques, performance evaluation and future directions](https://mlsanity.com/paper/2512.01171/) (2025)

## Abstract (arXiv)

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.