Goto

Collaborating Authors

CausalML: Python Package for Causal Machine Learning

arXiv.org Machine Learning

CausalML is a Python implementation of algorithms related to causal inference and machine learning. Algorithms combining causal inference and machine learning have been a trending topic in recent years. This package tries to bridge the gap between theoretical work on methodology and practical applications by making a collection of methods in this field available in Python. This paper introduces the key concepts, scope, and use cases of this package.


This Python Package 'Causal ML' Provides a Suite of Uplift Modeling and Causal Inference with Machine Learning MarkTechPost

#artificialintelligence

'Causal ML' is a Python package that deals with uplift modeling, which estimates heterogeneous treatment effect (HTE) and causal inference methods with the help of machine learning (ML) algorithms based on research. It uses a standard interface that allows users to estimate the Conditional Average Treatment Effect (CATE) or Individual Treatment Effect (ITE) from data (experimental or observational). 'Casual ML' package provides eight cutting edge uplift modeling algorithms combining causal inference & ML. 'Essentially, it estimates the causal impact of intervention T on outcome Y for users with observed features X, without strong assumptions on the model form'. As mentioned earlier, the package deals with uplift modeling, which estimates heterogeneous treatment effect (HTE), therefore starting with general causal inference, then learning about HTE and uplift modeling would definitely help.


uber/causalml

#artificialintelligence

This project is stable and being incubated for long-term support. It may contain new experimental code, for which APIs are subject to change. Causal ML is a Python package that provides a suite of uplift modeling and causal inference methods using machine learning algorithms based on recent research. It provides a standard interface that allows user to estimate the Conditional Average Treatment Effect (CATE) or Individual Treatment Effect (ITE) from experimental or observational data. Essentially, it estimates the causal impact of intervention T on outcome Y for users with observed features X, without strong assumptions on the model form.


Adapting Neural Networks for Uplift Models

arXiv.org Machine Learning

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.


Uplift Modeling from Separate Labels

arXiv.org Machine Learning

Uplift modeling is aimed at estimating the incremental impact of an action on an individual's behavior, which is useful in various application domains such as targeted marketing (advertisement campaigns) and personalized medicine (medical treatments). Conventional methods of uplift modeling require every instance to be jointly equipped with two types of labels: the taken action and its outcome. However, obtaining two labels for each instance at the same time is difficult or expensive in many real-world problems. In this paper, we propose a novel method of uplift modeling that is applicable to a more practical setting where only one type of labels is available for each instance. We demonstrate the effectiveness of the proposed method through experiments.