MMCE: A Framework for Deep Monotonic Modeling of Multiple Causal Effects

TL;DR

The paper tackles deriving multiple causal effects from observational data to guide incentive-driven ROI optimization when randomized trials are unavailable. It introduces MMCE, a deep monotonic framework that enforces monotonic priors and jointly models natural and incremental quantities to produce multiple price-response effects, combining a deep monotonic paradigm, an s-shaped network, and a structured training regime. The approach is validated with large-scale offline data and an online A/B test, showing improved monotonicity, uplift estimation, and a 12% ROI uplift in practice. This work enables more effective, data-driven allocation strategies in marketing under constraints, even without RCT data, by providing scalable networks and evaluative priors tailored to observational settings.

Abstract

When we plan to use money as an incentive to change the behavior of a person (such as making riders to deliver more orders or making consumers to buy more items), the common approach of this problem is to adopt a two-stage framework in order to maximize ROI under cost constraints. In the first stage, the individual price response curve is obtained. In the second stage, business goals and resource constraints are formally expressed and modeled as an optimization problem. The first stage is very critical. It can answer a very important question. This question is how much incremental results can incentives bring, which is the basis of the second stage. Usually, the causal modeling is used to obtain the curve. In the case of only observational data, causal modeling and evaluation are very challenging. In some business scenarios, multiple causal effects need to be obtained at the same time. This paper proposes a new observational data modeling and evaluation framework, which can simultaneously model multiple causal effects and greatly improve the modeling accuracy under some abnormal distributions. In the absence of RCT data, evaluation seems impossible. This paper summarizes three priors to illustrate the necessity and feasibility of qualitative evaluation of cognitive testing. At the same time, this paper innovatively proposes the conditions under which observational data can be considered as an evaluation dataset. Our approach is very groundbreaking. It is the first to propose a modeling framework that simultaneously obtains multiple causal effects. The offline analysis and online experimental results show the effectiveness of the results and significantly improve the effectiveness of the allocation strategies generated in real world marketing activities.

Figures (5)

• Figure 1: The relationship between the incentive amount and the number of completed orders under random data and observational data
• Figure 2: General deep monotonic model paradigm for causal effect estimation
• Figure 3: The simplest s-shaped network structure
• Figure 4: Differenct types of modeling
• Figure 5: MMCE