{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T09:58:36Z","timestamp":1775296716689,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2018,12,5]],"date-time":"2018-12-05T00:00:00Z","timestamp":1543968000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,12,5]],"date-time":"2018-12-05T00:00:00Z","timestamp":1543968000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIP1533983"],"award-info":[{"award-number":["IIP1533983"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ECCS1462245"],"award-info":[{"award-number":["ECCS1462245"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1007\/s10994-018-5768-3","type":"journal-article","created":{"date-parts":[[2018,12,5]],"date-time":"2018-12-05T12:04:54Z","timestamp":1544011494000},"page":"945-970","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Constructing effective personalized policies using counterfactual inference from biased data sets with many features"],"prefix":"10.1007","volume":"108","author":[{"given":"Onur","family":"Atan","sequence":"first","affiliation":[]},{"given":"William R.","family":"Zame","sequence":"additional","affiliation":[]},{"given":"Qiaojun","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Mihaela","family":"van der Schaar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,12,5]]},"reference":[{"key":"5768_CR1","unstructured":"Alaa, A.M., van\u00a0der Schaar, M. (2017). Bayesian inference of individualized treatment effects using multi-task gaussian processes. arXiv preprint arXiv:1704.02801"},{"key":"5768_CR2","unstructured":"Atan, O., Zame, W. R., & van\u00a0der Schaar, M. (2018). Learning optimal policies from observational data. arXiv preprint arXiv:1802.08679"},{"key":"5768_CR3","unstructured":"Athey, S., & Imbens, G. W. (2015). Recursive partitioning for heterogeneous causal effects. arXiv preprint arXiv:1504.01132 ."},{"issue":"19","key":"5768_CR4","doi-asserted-by":"publisher","first-page":"1876","DOI":"10.1016\/j.tcs.2009.01.016","volume":"410","author":"JY Audibert","year":"2009","unstructured":"Audibert, J. Y., Munos, R., & Szepesv\u00e1ri, C. (2009). Exploration\u2013exploitation tradeoff using variance estimates in multi-armed bandits. Theoretical Computer Science, 410(19), 1876\u20131902.","journal-title":"Theoretical Computer Science"},{"key":"5768_CR5","doi-asserted-by":"crossref","unstructured":"Beygelzimer, A., & Langford, J. (2009). The offset tree for learning with partial labels. In Proceedings of the 15th ACM SIGKDD international conference on knowledge discovery and data mining (pp. 129\u2013138).","DOI":"10.1145\/1557019.1557040"},{"issue":"1","key":"5768_CR6","first-page":"3207","volume":"14","author":"L Bottou","year":"2013","unstructured":"Bottou, L., Peters, J., Candela, J. Q., Charles, D. X., Chickering, M., Portugaly, E., et al. (2013). Counterfactual reasoning and learning systems: The example of computational advertising. Journal of Machine Learning Research, 14(1), 3207\u20133260.","journal-title":"Journal of Machine Learning Research"},{"key":"5768_CR7","volume-title":"Pattern classification","author":"RO Duda","year":"2012","unstructured":"Duda, R. O., Hart, P. E., & Stork, D. G. (2012). Pattern classification. Hoboken: Wiley."},{"key":"5768_CR8","unstructured":"Dud\u00edk, M., Langford, J., & Li, L. (2011). Doubly robust policy evaluation and learning. In International conference on machine learning (ICML)."},{"key":"5768_CR9","first-page":"845","volume":"5","author":"JG Dy","year":"2004","unstructured":"Dy, J. G., & Brodley, C. E. (2004). Feature selection for unsupervised learning. Journal of Machine Learning Research, 5, 845\u2013889.","journal-title":"Journal of Machine Learning Research"},{"key":"5768_CR10","unstructured":"Hall, M. A. (1999). Correlation-based feature selection for machine learning. PhD thesis, The University of Waikato"},{"key":"5768_CR11","unstructured":"He, X., Cai, D., & Niyogi, P. (2005). Laplacian score for feature selection. In Advances in neural information processing systems (pp. 507\u2013514)."},{"key":"5768_CR12","unstructured":"Hoiles, W., & van der Schaar, M. (2016). Bounded off-policy evaluation with missing data for course recommendation and curriculum design bounded off-policy evaluation with missing data for course recommendation and curriculum design. In International conference on machine learning (pp 1596\u20131604)."},{"issue":"2","key":"5768_CR13","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1198\/106186008X320456","volume":"17","author":"EL Ionides","year":"2008","unstructured":"Ionides, E. L. (2008). Truncated importance sampling. Journal of Computational and Graphical Statistics, 17(2), 295\u2013311.","journal-title":"Journal of Computational and Graphical Statistics"},{"key":"5768_CR14","unstructured":"Jiang, N., & Li, L. (2016). Doubly robust off-policy evaluation for reinforcement learning. In International conference on machine learning (ICML)."},{"key":"5768_CR15","unstructured":"Joachims, T., Grotov, A., Swaminathan, A., & de Rijke, M. (2018). Deep learning with logged bandit feedback. In International conference on learning representations (ICLR)."},{"key":"5768_CR16","doi-asserted-by":"crossref","unstructured":"Joachims, T., & Swaminathan, A. (2016). Counterfactual evaluation and learning for search, recommendation and ad placement. In International ACM SIGIR conference on research and development in information retrieval (pp 1199\u20131201).","DOI":"10.1145\/2911451.2914803"},{"key":"5768_CR17","unstructured":"Johansson, F., Shalit, U., & Sontag, D. (2016). Learning representations for counterfactual inference. In International conference on machine learning (ICML)"},{"key":"5768_CR18","doi-asserted-by":"crossref","unstructured":"Kira, K., & Rendell, L. A. (1992). A practical approach to feature selection. In Proceedings of the ninth international workshop on Machine learning (pp. 249\u2013256).","DOI":"10.1016\/B978-1-55860-247-2.50037-1"},{"key":"5768_CR19","unstructured":"Koller, D., & Sahami, M. (1996). Toward optimal feature selection. Stanford InfoLab."},{"key":"5768_CR20","unstructured":"Maurer, A., & Pontil, M. (2009). Empirical bernstein bounds and sample variance penalization. In The 22nd conference on learning theory."},{"issue":"8","key":"5768_CR21","doi-asserted-by":"publisher","first-page":"1226","DOI":"10.1109\/TPAMI.2005.159","volume":"27","author":"H Peng","year":"2005","unstructured":"Peng, H., Long, F., & Ding, C. (2005). Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(8), 1226\u20131238.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"5768_CR22","doi-asserted-by":"publisher","first-page":"599","DOI":"10.2307\/2529748","volume":"32","author":"R Prentice","year":"1976","unstructured":"Prentice, R. (1976). Use of the logistic model in retrospective studies. Biometrics, 32(3), 599\u2013606.","journal-title":"Biometrics"},{"issue":"1\u20132","key":"5768_CR23","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1023\/A:1025667309714","volume":"53","author":"M Robnik-\u0160ikonja","year":"2003","unstructured":"Robnik-\u0160ikonja, M., & Kononenko, I. (2003). Theoretical and empirical analysis of relieff and rrelieff. Machine Learning, 53(1\u20132), 23\u201369.","journal-title":"Machine Learning"},{"issue":"1","key":"5768_CR24","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1093\/biomet\/70.1.41","volume":"70","author":"PR Rosenbaum","year":"1983","unstructured":"Rosenbaum, P. R., & Rubin, D. B. (1983). The central role of the propensity score in observational studies for causal effects. Biometrika, 70(1), 41\u201355.","journal-title":"Biometrika"},{"key":"5768_CR25","unstructured":"Shalit, U., Johansson, F., & Sontag, D. (2016). Estimating individual treatment effect: Generalization bounds and algorithms. arXiv preprint arXiv:1606.03976"},{"issue":"1","key":"5768_CR26","first-page":"2533","volume":"15","author":"A Slivkins","year":"2014","unstructured":"Slivkins, A. (2014). Contextual bandits with similarity information. Journal of Machine Learning Research, 15(1), 2533\u20132568.","journal-title":"Journal of Machine Learning Research"},{"issue":"May","key":"5768_CR27","first-page":"1393","volume":"13","author":"L Song","year":"2012","unstructured":"Song, L., Smola, A., Gretton, A., Bedo, J., & Borgwardt, K. (2012). Feature selection via dependence maximization. Journal of Machine Learning Research, 13(May), 1393\u20131434.","journal-title":"Journal of Machine Learning Research"},{"key":"5768_CR28","unstructured":"Strehl, A., Langford, J., Li, L., & Kakade S. M. (2010). Learning from logged implicit exploration data. In Advances in neural information processing systems (pp. 2217\u20132225)."},{"key":"5768_CR29","first-page":"1731","volume":"16","author":"A Swaminathan","year":"2015","unstructured":"Swaminathan, A., & Joachims, T. (2015). Batch learning from logged bandit feedback through counterfactual risk minimization. Journal of Machine Learning Research, 16, 1731\u20131755.","journal-title":"Journal of Machine Learning Research"},{"key":"5768_CR30","unstructured":"Swaminathan, A., & Joachims, T. (2015b). The self-normalized estimator for counterfactual learning. In advances in neural information processing systems (pp. 3231\u20133239)."},{"key":"5768_CR31","unstructured":"Tang, J., Alelyani, S., & Liu, H. (2014). Feature selection for classification: A review. Data Classification: Algorithms and Applications, 37."},{"key":"5768_CR32","unstructured":"Tekin, C., & van\u00a0der Schaar, M. (2014). Discovering, learning and exploiting relevance. In Advances in neural information processing systems (pp. 1233\u20131241)."},{"key":"5768_CR33","unstructured":"Tian, L., Alizadeh, A., Gentles, A., & Tibshirani, R. (2012). A simple method for detecting interactions between a treatment and a large number of covariates. arXiv preprint arXiv:1212.2995"},{"key":"5768_CR34","unstructured":"Wager, S., & Athey, S. (2015). Estimation and inference of heterogeneous treatment effects using random forests. arXiv preprint arXiv:1510.04342"},{"key":"5768_CR35","unstructured":"Weissman, T., Ordentlich, E., Seroussi, G., Verdu, S., & Weinberger, M. J. (2003). Inequalities for the l1 deviation of the empirical distribution. Hewlett-Packard Labs, Tech Rep."},{"key":"5768_CR36","first-page":"1439","volume":"3","author":"J Weston","year":"2003","unstructured":"Weston, J., Elisseeff, A., Sch\u00f6lkopf, B., & Tipping, M. (2003). Use of the zero-norm with linear models and kernel methods. Journal of Machine Learning Research, 3, 1439\u20131461.","journal-title":"Journal of Machine Learning Research"},{"issue":"3\u20134","key":"5768_CR37","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1023\/A:1022672621406","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3\u20134), 229\u2013256.","journal-title":"Machine Learning"},{"issue":"7","key":"5768_CR38","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1109\/TNN.2010.2047114","volume":"21","author":"Z Xu","year":"2010","unstructured":"Xu, Z., King, I., Lyu, M. R. T., & Jin, R. (2010). Discriminative semi-supervised feature selection via manifold regularization. IEEE Transactions on Neural Networks, 21(7), 1033\u20131047.","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"4","key":"5768_CR39","doi-asserted-by":"publisher","first-page":"1133","DOI":"10.1109\/JBHI.2016.2574857","volume":"21","author":"J Yoon","year":"2017","unstructured":"Yoon, J., Davtyan, C., & van der Schaar, M. (2017). Discovery and clinical decision support for personalized healthcare. IEEE Journal of Biomedical and Health Informatics, 21(4), 1133\u20131145.","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"5768_CR40","first-page":"856","volume":"3","author":"L Yu","year":"2003","unstructured":"Yu, L., & Liu, H. (2003). Feature selection for high-dimensional data: A fast correlation-based filter solution. International Conference on Machine Learning (ICML), 3, 856\u2013863.","journal-title":"International Conference on Machine Learning (ICML)"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-018-5768-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10994-018-5768-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-018-5768-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T09:20:53Z","timestamp":1775294453000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10994-018-5768-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,5]]},"references-count":40,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2019,6]]}},"alternative-id":["5768"],"URL":"https:\/\/doi.org\/10.1007\/s10994-018-5768-3","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,5]]},"assertion":[{"value":"15 December 2016","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 October 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}