一直以來機器學習但願解決的一個問題就是'what if',也就是決策指導:html
這類問題之因此難以解決是由於ground truth在現實中是觀測不到的,一個已經服了藥的患者血壓下降但咱們無從知道在同一時刻若是他沒有服藥血壓是否是也會下降。git
這個時候作分析的同窗應該會說咱們作AB實驗!咱們估計總體差別,顯著就是有效,不顯著就是無效。但咱們能作的只有這些麼?github
固然不是!由於每一個個體都是不一樣的!總體無效不意味着局部羣體無效!dom
如下方法從不一樣的角度嘗試解決這個問題,但基本思路是一致的:咱們沒法觀測到每一個用戶的treatment effect,但咱們能夠找到一羣類似用戶來估計實驗對他們的影響。機器學習
我會在以後的博客中,從CasualTree的第二篇Recursive partitioning for heterogeneous causal effects開始梳理下述方法中的異同。學習
整個領域還在發展中,幾個開源代碼都剛release不久,因此這個博客也會持續更新。若是你們看到好的文章和工程實現也歡迎在下面評論~spa
Nicholas J Radcliffe and Patrick D Surry. Real-world uplift modelling with significance based uplift trees. White Paper TR-2011-1, Stochastic Solutions, 2011.[文章連接]rest
Yan Zhao, Xiao Fang, and David Simchi-Levi. Uplift modeling with multiple treatments and general response types. Proceedings of the 2017 SIAM International Conference on Data Mining, SIAM, 2017. [文章連接] [Github連接]htm
Athey, S., and Imbens, G. W. 2015. Machine learning methods for
estimating heterogeneous causal effects. stat 1050(5) [文章連接]blog
Athey, S., and Imbens, G. 2016. Recursive partitioning for heterogeneous causal effects. Proceedings of the National Academy of
Sciences. [文章連接] [Github連接] [paper慢慢讀]
C. Tran and E. Zheleva, 「Learning triggers for heterogeneous treatment effects,」 in Proceedings of the AAAI Conference on Artificial Intelligence, 2019 [文章連接] [Github連接] [paper慢慢讀]
M. Oprescu, V. Syrgkanis and Z. S. Wu. Orthogonal Random Forest for Causal Inference. Proceedings of the 36th International Conference on Machine Learning (ICML), 2019 [文章連接] [GitHub連接]
Sören R. Künzel, Jasjeet S. Sekhon, Peter J. Bickel, and Bin Yu. Metalearners for estimating heterogeneous treatment effects using machine learning. Proceedings of the National Academy of Sciences, 2019. [文章連接] [GitHub連接]