DCRMTA: Deep Causal Representation Learning for Multi-Touch Attribution
Deep Causal Representation for MTA (DCRMTA), an end-to-end framework that explicitly quantifies and preserves the causal impact of user features, is proposed, which effectively improves predictive accuracy and provides robust, Shapley-based credit allocations across complex marketing channels.
Jia-Ming Tang, Jing-Xuan Wen, L. Jing
· 2 citations