【Uplift】参考资料篇

大家好，欢迎来到IT知识分享网。

https://zhuanlan.zhihu.com/p/358582762

博客等

• 腾讯广告-uplift广告增效衡量说明

https://e.qq.com/ads/adfaq/delivery/tool/08/

https://morketing.com/detail/4704

• 一文读懂Uplift

https://mp.weixin.qq.com/s/FOVggFduHKeDr3jidcmqgA

基本是综述论文翻译一遍

• 滴滴：DiDi Food中的智能补贴实战漫谈

https://mp.weixin.qq.com/s/WU1iILMFdH3RZAbJKFU4WA

树分裂的部分讲的比较详细，方便理解

• 因果推断简介（丁鹏）

https://yao-lab.github.io/2009.fall.pku/lecture10_DingP_causal091101.pdf

论文

• Causal Inference and Uplift Modeling A review of the literature

http://proceedings.mlr.press/v67/gutierrez17a.html

综述论文，很经典

• A Survey on Causal Inference

https://arxiv.org/abs/2002.02770

综述论文，比较新

• A Large Scale Benchmark for Uplift Modeling

http://ama.imag.fr/~amini/Publis/large-scale-benchmark.pdf

数据集，有AUUC和Qini的具体公式，注意和前面的综述不太一致

• Metalearners for estimating heterogeneous treatment effects using machine learning

https://arxiv.org/abs/1706.03461

X-Learner，有S-Learner和T-Learner的介绍

• Quasi-Oracle Estimation of Heterogeneous Treatment Effects

https://arxiv.org/abs/1712.04912

R-Learner

• Feature Selection Methods for Uplift Modeling

https://arxiv.org/abs/2005.03447

特征筛选方法

• Adapting Neural Networks for the Estimation of Treatment Effects

https://arxiv.org/abs/1906.02120

DragonNet

• Decision trees for uplift modeling with single and multiple treatments

https://link.springer.com/article/10.1007/s10115-011-0434-0

UpliftTree

• Estimation and Inference of Heterogeneous Treatment Effects using Random Forests

http://bayes.acs.unt.edu:8083/BayesContent/class/rich/articles/Estimation_And_Inference_Of_Heterogeneous_Treatment_Effects_Using_Random_Forests.pdf

CausalForest

• Uplift Modeling with Multiple Treatments and General Response Types

https://arxiv.org/abs/1705.08492

CTS，一种tree-based的方法

• Free Lunch! Retrospective Uplift Modeling for Dynamic Promotions Recommendation within ROI Constraints

https://arxiv.org/abs/2008.06293

一个发券应用，据说可以只用正样本就可以

调包

• Causal ML

https://causalml.readthedocs.io/en/latest/about.html

Uber开源的一个包，实现了Meta-Learner和Tree-based方法、特征筛选、评估

• DoWhy

https://microsoft.github.io/dowhy/readme.html

微软的，没用过，看着还比较全

• 其他还有pylift、EconML，还有R的一些实现的包

其他资源

• coursera课程：A Crash Course in Causality: Inferring Causal Effects from Observational Data

https://www.coursera.org/learn/crash-course-in-causality/home/week/1

入门款

• awesome-causality-algorithms

https://github.com/rguo12/awesome-causality-algorithms

一个汇总资源的github

• 因果推断入门

https://www.bilibili.com/video/BV1sJ41177sg

B站，一个up对Causal Inference in Statistics: A Primer的解说，连载中

• Introduction to Causal Inference

https://www.bradyneal.com/causal-inference-course

一个大佬的因果推断课程