Adapting Neural Networks for Uplift Models

TL;DR

This paper introduces a neural network-based method for uplift modeling, improving the estimation of individual treatment effects in marketing data by jointly optimizing multiple loss functions.

Contribution

It presents a novel neural network approach that jointly optimizes uplift and outcome prediction, reducing overfitting compared to traditional tree-based methods.

Findings

Improved uplift estimation on synthetic data

Enhanced performance on real marketing datasets

Joint optimization reduces overfitting

Abstract

Uplift is a particular case of individual treatment effect modeling. Such models deal with cause-and-effect inference for a specific factor, such as a marketing intervention. In practice, these models are built on customer data who purchased products or services to improve product marketing. Uplift is estimated using either i) conditional mean regression or ii) transformed outcome regression. Most existing approaches are adaptations of classification and regression trees for the uplift case. However, in practice, these conventional approaches are prone to overfitting. Here we propose a new method using neural networks. This representation allows to jointly optimize the difference in conditional means and the transformed outcome losses. As a consequence, the model not only estimates the uplift, but also ensures consistency in predicting the outcome. We focus on fully randomized experiments, which is the case of our data. We show our proposed method improves the state-of-the-art on synthetic and real data.