CausalMMM: Learning Causal Structure for Marketing Mix Modeling

TL;DR

CausalMMM introduces a novel approach to automatically discover interpretable causal structures in marketing mix modeling, improving GMV prediction accuracy by integrating Granger causality with a variational inference framework that accounts for marketing response patterns.

Contribution

It proposes a new causal MMM method that dynamically learns causal structures across different shops and incorporates known marketing response patterns, overcoming prior limitations of fixed causal assumptions.

Findings

Achieves 5.7% to 7.1% improvement in causal structure learning on synthetic data.

Enhances GMV prediction accuracy on an e-commerce platform.

Effectively models diverse causal structures and marketing response patterns.

Abstract

In online advertising, marketing mix modeling (MMM) is employed to predict the gross merchandise volume (GMV) of brand shops and help decision-makers to adjust the budget allocation of various advertising channels. Traditional MMM methods leveraging regression techniques can fail in handling the complexity of marketing. Although some efforts try to encode the causal structures for better prediction, they have the strict restriction that causal structures are prior-known and unchangeable. In this paper, we define a new causal MMM problem that automatically discovers the interpretable causal structures from data and yields better GMV predictions. To achieve causal MMM, two essential challenges should be addressed: (1) Causal Heterogeneity. The causal structures of different kinds of shops vary a lot. (2) Marketing Response Patterns. Various marketing response patterns i.e., carryover effect and shape effect, have been validated in practice. We argue that causal MMM needs dynamically discover specific causal structures for different shops and the predictions should comply with the prior known marketing response patterns. Thus, we propose CausalMMM that integrates Granger causality in a variational inference framework to measure the causal relationships between different channels and predict the GMV with the regularization of both temporal and saturation marketing response patterns. Extensive experiments show that CausalMMM can not only achieve superior performance of causal structure learning on synthetic datasets with improvements of 5.7%\sim 7.1%, but also enhance the GMV prediction results on a representative E-commerce platform.