{"id":31708,"date":"2022-01-14T21:47:24","date_gmt":"2022-01-14T13:47:24","guid":{"rendered":"https:\/\/swarma.org\/?p=31708"},"modified":"2022-01-14T21:47:24","modified_gmt":"2022-01-14T13:47:24","slug":"causalml%e5%88%9b%e5%a7%8b%e4%ba%ba%e8%b5%b5%e6%8c%af%e5%ae%87%ef%bc%9a%e5%9f%ba%e4%ba%8epython%e7%9a%84%e5%bc%80%e6%ba%90%e6%a1%86%e6%9e%b6%e7%8e%a9%e8%bd%ac%e5%9b%a0%e6%9e%9c%e5%ad%a6%e4%b9%a0","status":"publish","type":"post","link":"https:\/\/swarma.org\/?p=31708","title":{"rendered":"CausalML\u521b\u59cb\u4eba\u8d75\u632f\u5b87\uff1a\u57fa\u4e8ePython\u7684\u5f00\u6e90\u6846\u67b6\u73a9\u8f6c\u56e0\u679c\u5b66\u4e60 | \u5468\u65e5\u76f4\u64ad\u00b7\u56e0\u679c\u79d1\u5b66\u8bfb\u4e66\u4f1a"},"content":{"rendered":"
\n
\n
\n

<\/p>\n

\n
\n
\n
\n
\n
\n

<\/section>\n<\/section>\n
\n
\n

\u5bfc\u8bed<\/strong><\/span><\/p>\n<\/section>\n<\/section>\n

\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
\n
\n
\n
\u57fa\u4e8e\u878d\u5408\u673a\u5668\u5b66\u4e60\u548c\u56e0\u679c\u63a8\u65ad\u65b9\u6cd5\u7684\u56e0\u679c\u5b66\u4e60\u5df2\u9010\u6e10\u6210\u4e3a\u7814\u7a76\u9886\u57df\u548c\u4e1a\u754c\u5e94\u7528\u7684\u4e00\u4e2a\u70ed\u70b9\u533a\u57df\u3002<\/span>\u5728\u8fd9\u4e2a\u65b9\u5411\uff0c\u6211\u4eec\u5e0c\u671b\u6709\u7c7b\u4f3csklearn\u4e4b\u4e8e\u673a\u5668\u5b66\u4e60\u90a3\u6837\u597d\u7528\u7684\u5de5\u5177\u5305\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u7b80\u5355\u7684\u5e94\u7528\u5404\u4e2a\u6a21\u578b\u3002<\/span>\u672c\u5468\u65e5\u4e0a\u53489\u70b9\uff0c<\/span><\/strong>\u8bfb\u4e66\u4f1a<\/strong><\/a>\u9080\u8bf7\u5230CausalML\u521b\u59cb\u56e2\u961f\u7684\u8d75\u632f\u5b87\uff0c\u4e3a\u6211\u4eec\u4ecb\u7ecdCausalML\u4f5c\u4e3a\u4e00\u4e2a\u57fa\u4e8ePython\u7684\u5f00\u6e90\u9879\u76ee\u7684\u53d1\u5c55\u5386\u7a0b\uff0c\u6838\u5fc3\u65b9\u6cd5\uff0c\u4ee5\u53ca\u5e94\u7528\u573a\u666f\u3002<\/span><\/strong><\/section>\n

<\/span><\/strong><\/section>\n

\u7531\u667a\u6e90\u793e\u533a\u3001\u96c6\u667a\u4ff1\u4e50\u90e8\u8054\u5408\u4e3e\u529e\u7684<\/strong>\u56e0\u679c\u79d1\u5b66\u4e0eCausal AI\u8bfb\u4e66\u4f1a\u7b2c\u4e09\u5b63<\/strong><\/a>\uff0c\u5176\u76ee\u6807\u662f\uff1a\u5c06\u4e3b\u8981\u7ed3\u5408\u56e0\u679c\u63a8\u65ad\u7684\u6f5c\u5728\u7ed3\u679c\uff08Potential Outcomes\uff09\u6846\u67b6\u5c55\u5f00\u8ba8\u8bba\uff0c\u5e76\u5c1d\u8bd5\u5728\u4e0d\u540c\u9886\u57df\uff0c\u5305\u62ec\u4f46\u4e0d\u9650\u4e8e\u533b\u5b66\u3001\u7ecf\u6d4e\u5b66\u3001\u673a\u5668\u5b66\u4e60\u7b49\u9886\u57df\uff0c\u5c1d\u8bd5\u5efa\u7acb\u4e0eSCM\u7684\u5bf9\u5e94\u5173\u7cfb\u3002\u8bfb\u4e66\u81ea2021\u5e7410\u670824\u65e5\u5f00\u59cb\uff0c\u6bcf\u5468\u65e5\u4e0a\u5348 09:00-11:00\u4e3e\u529e\uff0c\u6301\u7eed\u65f6\u95f4\u9884\u8ba1 2-3 \u4e2a\u6708\u3002<\/strong><\/p>\n

<\/strong><\/strong><\/span><\/strong><\/strong><\/section>\n<\/section>\n<\/section>\n<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
\n
<\/section>\n<\/section>\n
\n

<\/section>\n<\/section>\n
<\/section>\n

<\/section>\n

<\/section>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u80cc\u666f<\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n


<\/p>\n

<\/span><\/h1>\n

\u56e0\u679c\u5b66\u4e60\uff08causal learning\uff09\u662f\u4e00\u4e2a\u878d\u5408\u4e86\u56e0\u679c\u63a8\u65ad\u548c\u673a\u5668\u5b66\u4e60\u7684\u9886\u57df\uff0c\u5305\u542b\u5f88\u591a\u65b9\u6cd5\uff0c\u5176\u4e2duplift\u6a21\u578b\u662f\u4e00\u4e2a\u91cd\u8981\u65b9\u6cd5\uff0c\u5728\u4e1a\u754c\u6709\u7740\u4e30\u5bcc\u7684\u5e94\u7528\u573a\u666f\u3002\u65e9\u57282018\u5e74\uff0cUber\u7684\u6570\u636e\u79d1\u5b66\u56e2\u961f\u9762\u4e34\u9700\u8981uplift\u6a21\u578b\u89e3\u51b3\u7684\u95ee\u9898\uff0c\u5728\u6ca1\u6709\u627e\u5230\u5408\u9002\u7684\u5f00\u6e90\u5de5\u5177\u5305\u7684\u60c5\u51b5\u4e0b\uff0c\u5f00\u53d1\u4e86CausalML\uff0c\u968f\u540e\u4f5c\u4e3a\u5f00\u6e90\u9879\u76ee\u63d0\u4f9b\u7ed9\u66f4\u5e7f\u6cdb\u7684\u793e\u533a\u4f7f\u7528\uff0c\u4e5f\u5438\u5f15\u6765\u66f4\u591a\u7684\u5f00\u53d1\u8005\u5b8c\u5584\u4e86\u8fd9\u4e2a\u5de5\u5177\u5305\u3002\u76ee\u524d\uff0cCausalML\u5df2\u6709\u8d85\u8fc760\u4e07\u7684\u4e0b\u8f7d\u91cf\uff0c\u5f00\u6e90\u9879\u76ee\u7ec4\u4e5f\u5728\u6301\u7eed\u7ef4\u62a4\u548c\u5347\u7ea7\u8fd9\u4e2a\u5de5\u5177\u5305\u3002<\/span><\/p>\n


<\/span><\/p>\n

CausalML\u6700\u521d\u662f\u4e3a\u4e86\u89e3\u51b3\u4ec0\u4e48\u95ee\u9898\u800c\u5efa\u8bbe\u7684\uff1f\u5176\u4e2d\u5305\u542b\u54ea\u4e9b\u65b9\u6cd5\uff1f\u53ef\u4ee5\u5e94\u7528\u4e8e\u54ea\u4e9b\u573a\u666f\uff1f\u5e0c\u671b\u901a\u8fc7\u8fd9\u6b21\u5206\u4eab\uff0c\u8ba9\u5927\u5bb6\u4e86\u89e3\u5230\u66f4\u591a\u7684\u5173\u4e8eCausalML\u7684\u4fe1\u606f\u548c\u7528\u6cd5\u3002<\/span><\/p>\n


<\/span><\/p>\n


<\/span><\/p>\n

\n
\n
\n
\n
\n

<\/section>\n

<\/section>\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n
\n

\u5185\u5bb9\u7b80\u4ecb<\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n


<\/p>\n

\u8fd9\u6b21\u5206\u4eab\u4e3b\u8981\u5206\u4e3a\u4e94\u4e2a\u90e8\u5206\uff1a<\/span><\/section>\n
    \n
  1. \n
    CausalML\u7f18\u8d77\uff1aCausalML\u6700\u521d\u662f\u5982\u4f55\u5efa\u7acb\u8d77\u6765\u7684\uff1f<\/span><\/section>\n<\/li>\n
  2. \n
    \u4e3b\u8981\u6a21\u5757\uff1aCausalML\u5185\u5305\u542b\u4ec0\u4e48\u6a21\u578b\uff1f\u4ec0\u4e48\u662fuplift\u6a21\u578b\uff1f\u6709\u54ea\u4e9bCausalML\u7279\u6709\u7684\u65b9\u6cd5\uff1f<\/span><\/section>\n<\/li>\n
  3. \n
    \u5b9e\u64cdDemo: \u901a\u8fc7\u4e00\u4e9b\u4ee3\u7801\u6848\u4f8b\uff0c\u4ecb\u7ecd\u5982\u4f55\u4f7f\u7528CausalML<\/span><\/section>\n<\/li>\n
  4. \n
    \u5e94\u7528\u573a\u666f\uff1aCausalML\u53ef\u4ee5\u5e94\u7528\u4e8e\u5b9e\u8df5\u4e2d\u54ea\u4e9b\u573a\u666f\uff1f<\/span><\/section>\n<\/li>\n
  5. \n

    \u603b\u7ed3\u548c\u5c55\u671b\uff1aCausalML\u672a\u6765\u7684\u53d1\u5c55\u65b9\u5411\u6709\u54ea\u4e9b\uff1f\u6b22\u8fce\u5927\u5bb6\u53c2\u4e0e\u5171\u5efa\uff0c\u6216\u5206\u4eab\u4f7f\u7528CausalML\u7684\u6545\u4e8b\u548c\u6848\u4f8b\uff01<\/span><\/p>\n<\/li>\n<\/ol>\n


    <\/h1>\n


    <\/p>\n

    \n
    \n
    \n
    \n
    \n

    <\/section>\n

    <\/section>\n
    \n
    <\/svg><\/section>\n<\/section>\n<\/section>\n
    \n

    \u4e3b\u8bb2\u4eba <\/strong><\/strong><\/p>\n<\/section>\n

    \n

    <\/section>\n

    <\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n


    <\/p>\n

    <\/p>\n

    \u8d75\u632f\u5b87<\/span><\/strong>\uff0c\u817e\u8baf\u6570\u636e\u79d1\u5b66\u603b\u76d1\u3002\u5148\u540e\u5728Yahoo\uff0cUber\uff0c\u817e\u8baf\u4efb\u804c\u3002\u8d1f\u8d23\u5b9e\u9a8c\u3001\u56e0\u679c\u63a8\u65ad\u3001\u673a\u5668\u5b66\u4e60\u3001\u4ea7\u54c1\u5206\u6790\u3001\u5e73\u53f0\u5efa\u8bbe\u3001\u5f00\u6e90\u8f6f\u4ef6\u3001\u5e94\u7528\u7814\u7a76\u65b9\u9762\u7684\u5de5\u4f5c\u3002CausalML\u53d1\u8d77\u8005\u4e4b\u4e00\uff0c\u300a\u5173\u952e\u8fed\u4ee3\u53ef\u4fe1\u8d56\u7684\u7ebf\u4e0a\u5bf9\u7167\u5b9e\u9a8c\u300b\u8bd1\u8005\u4e4b\u4e00\u3002<\/span><\/p>\n


    <\/h1>\n

    \u53c2\u8003\u6587\u732e<\/span><\/strong><\/span><\/span><\/h1>\n
    \u5de5\u5177\u5305Git:<\/span><\/section>\n
    https:\/\/github.com\/uber\/causalml<\/span><\/section>\n
    \u53c2\u8003\u6587\u732e\uff08\u4f18\u5148\u9009\u8bfb14\u300115\u300116\uff09\uff1a<\/span><\/section>\n
    [1] Ahmed Alaa and Mihaela Schaar. Limits of estimating heterogeneous treatment effects: guidelines for practical algorithm design. In International Conference on Machine Learning, 129\u2013138. 2018.<\/span><\/section>\n
    [2] Susan Athey and Guido Imbens. Recursive partitioning for heterogeneous causal effects. Proceedings of the National Academy of Sciences, 113(27):7353\u20137360, 2016.<\/span><\/section>\n
    [3] Susan Athey, Julie Tibshirani, Stefan Wager, and others. Generalized random forests. The Annals of Statistics, 47(2):1148\u20131178, 2019.<\/span><\/section>\n
    [4] Susan Athey and Stefan Wager. Efficient policy learning. arXiv preprint arXiv:1702.02896, 2017.<\/span><\/section>\n
    [5] Pierre Gutierrez and Jean-Yves Gerardy. Causal inference and uplift modeling a review of the literature. JMLR: Workshop and Conference Proceedings 67, 2016.<\/span><\/section>\n
    [6] Jason Hartford, Greg Lewis, Kevin Leyton-Brown, and Matt Taddy. Deep iv: a flexible approach for counterfactual prediction. In Proceedings of the 34th International Conference on Machine Learning-Volume 70, 1414\u20131423. JMLR. org, 2017.<\/span><\/section>\n
    [7] Guido W Imbens and Jeffrey M Wooldridge. Recent developments in the econometrics of program evaluation. Journal of economic literature, 47(1):5\u201386, 2009.<\/span><\/section>\n
    [8] S\u00f6ren R K\u00fcnzel, 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, 116(10):4156\u20134165, 2019.<\/span><\/section>\n
    [9] Xinkun Nie and Stefan Wager. Quasi-oracle estimation of heterogeneous treatment effects. arXiv preprint arXiv:1712.04912, 2017.<\/span><\/section>\n
    [10] Miruna Oprescu, Vasilis Syrgkanis, and Zhiwei Steven Wu. Orthogonal random forest for heterogeneous treatment effect estimation. CoRR, 2018. URL: http:\/\/arxiv.org\/abs\/1806.03467, arXiv:1806.03467.<\/span><\/section>\n
    [11] Piotr Rzepakowski and Szymon Jaroszewicz. Decision trees for uplift modeling with single and multiple treatments. Knowl. Inf. Syst., 32(2):303\u2013327, August 2012.<\/span><\/section>\n
    [12] Yan Zhao, Xiao Fang, and David Simchi-Levi. Uplift modeling with multiple treatments and general response types. In Proceedings of the 2017 SIAM International Conference on Data Mining, 588\u2013596. SIAM, 2017. https:\/\/arxiv.org\/abs\/1705.08492<\/span><\/section>\n
    [13] Hahn, P. Richard, Jared S. Murray, and Carlos M. Carvalho. “Bayesian Regression Tree Models for Causal Inference: Regularization.” Confounding, and Heterogeneous Effects 1706 (2017).<\/span><\/section>\n
    [14] Chen, Huigang, Totte Harinen, Jeong-Yoon Lee, Mike Yung, and Zhenyu Zhao. “Causalml: Python package for causal machine learning.” arXiv preprint arXiv:2002.11631 (2020). https:\/\/arxiv.org\/abs\/2002.11631<\/span><\/section>\n
    [15] Zhao, Zhenyu, Yumin Zhang, Totte Harinen, and Mike Yung. “Feature Selection Methods for Uplift Modeling.” arXiv preprint arXiv:2005.03447 (2020).<\/span><\/section>\n
    [16] Zhao, Zhenyu, and Totte Harinen. “Uplift modeling for multiple treatments with cost optimization.” In 2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA), pp. 422-431. IEEE, 2019.<\/span><\/section>\n


    <\/p>\n


    <\/section>\n

    \n
    \n
    \n
    \n
    \n

    <\/section>\n

    <\/section>\n
    \n
    <\/svg><\/section>\n<\/section>\n<\/section>\n
    \n

    \u76f4\u64ad\u4fe1\u606f<\/strong><\/strong><\/p>\n<\/section>\n

    \n

    <\/section>\n

    <\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/h3>\n


    <\/p>\n

    \u65f6\u95f4\uff1a<\/span><\/strong><\/p>\n

    2022\u5e741\u670816\u65e5\u4e0a\u53489: 00-11: 00<\/span><\/p>\n


    <\/span><\/section>\n

    \u53c2\u4e0e\u65b9\u5f0f\uff1a<\/span><\/strong><\/p>\n