{"type":"ScholarlyArticle","title":"Causal Inference in Time Series via Supervised Learning","authors":[{"name":"Yoichi Chikahara","slug":"yoichi-chikahara","given":"Yoichi","family":"Chikahara","affiliation":"NTT Communication Science Laboratories , Kyoto 619-0237 , Japan"},{"name":"Akinori Fujino","slug":"akinori-fujino","given":"Akinori","family":"Fujino","affiliation":"NTT Communication Science Laboratories , Kyoto 619-0237 , Japan"}],"abstract":"Causal inference in time series is an important problem in many fields. Traditional methods use regression models for this problem. The inference accuracies of these methods depend greatly on whether or not the model can be well fitted to the data, and therefore we are required to select an appropriate regression model, which is difficult in practice. This paper proposes a supervised learning framework that utilizes a classifier instead of regression models. We present a feature representation that employs the distance between the conditional distributions given past variable values and show experimentally that the feature representation provides sufficiently different feature vectors for time series with different causal relationships. Furthermore, we extend our framework to multivariate time series and present experimental results where our method outperformed the model-based methods and the supervised learning method for i.i.d. data.","doi":"10.24963/ijcai.2018/282","url":"https://ijcai.org/proceedings/2018/282","pdf":"https://ijcai.org/proceedings/2018/0282.pdf","markdown":"https://ijcai.org/proceedings/2018/282.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/282","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Machine Learning","track":"Main track","number":282,"pages":{"first":2042,"last":2048},"keywords":["Machine Learning: Time-series;Data Streams","Machine Learning: Classification","Knowledge Representation and Reasoning: Action, Change and Causality"],"videos":[],"references":[{"position":1,"raw":"[Bell et al., 1996] David Bell, Jim Kay, and Jim Malley. A non- parametric approach to non-linear causality testing. Economics Letters, 51(1):7-18, 1996.","title":"A nonparametric approach to non-linear causality testing","authors":"David Bell, Jim Kay, Jim Malley","year":"1996","venue":"Economics Letters","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bontempi and Flauder, 2015] Gianluca Bontempi and Maxime Flauder. From dependency to causality: a machine learning ap- proach. JMLR, 16:2437-2457, 2015.","title":"From dependency to causality: a machine learning approach","authors":"Flauder Bontempi, Gianluca Bontempi, Maxime Flauder","year":"2015","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen and An, 1997] Min Chen and Hong Zhi An. A Kolmogorov- Smirnov type test for conditional heteroskedasticity in time se- ries. Statistics & probability letters, 33(3):321-331, 1997.","title":"A Kolmogorov-Smirnov type test for conditional heteroskedasticity in time series","authors":"Chen, An ;, Min Chen, Hong Zhi, An","year":"1997","venue":"Statistics & probability letters","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cheng et al., 2014] Dehua Cheng, Mohammad Taha Bahadori, and Yan Liu. FBLG: a simple and effective approach for tempo- ral dependence discovery from time series data. In KDD, pages 382-391, 2014.","title":"FBLG: a simple and effective approach for temporal dependence discovery from time series data","authors":"Dehua Cheng, Mohammad Taha Bahadori, Yan Liu","year":"2014","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Geweke, 1984] John F. Geweke. Measures of conditional linear dependence and feedback between time series. Journal of the American Statistical Association, 79(388):907-915, 1984.","title":"Measures of conditional linear dependence and feedback between time series","authors":"John F Geweke","year":"1984","venue":"Journal of the American Statistical Association","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Granger, 1969] Clive WJ Granger. Investigating causal relations by econometric models and cross-spectral methods. Economet- rica: Journal of the Econometric Society, pages 424-438, 1969.","title":"Investigating causal relations by econometric models and cross-spectral methods","authors":"Clive Wj Granger","year":"1969","venue":"Econometrica: Journal of the Econometric Society","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gretton et al., 2007] Arthur Gretton, Karsten M. Borgwardt, Malte Rasch, Bernhard Schölkopf, and Alex J. Smola. A kernel method for the two-sample-problem. In NIPS, pages 513-520, 2007.","title":"A kernel method for the two-sample-problem","authors":"Arthur Gretton, Karsten M Borgwardt, Malte Rasch, Bernhard Schölkopf, Alex J Smola","year":"2007","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Guyon, 2013] Isabelle Guyon. ChaLearn cause-effect pair chal- lenge. https://www.kaggle.com/c/cause-effect-pairs/, 2013.","title":"ChaLearn cause-effect pair challenge","authors":"Isabelle Guyon","year":null,"venue":null,"doi":null,"url":"https://www.kaggle.com/c/cause-effect-pairs/,2013","internal_url":null},{"position":9,"raw":"Jakob, ] Zscheischler Jakob. Database with cause-effect pairs. https://webdav.tuebingen.mpg.de/cause-effect/. [Janzing and Scholkopf, 2010] Dominik Janzing and Bernhard Scholkopf. Causal inference using the algorithmic Markov con- dition. IEEE Transactions on Information Theory, 56(10):5168- 5194, 2010.","title":"Causal inference using the algorithmic Markov condition","authors":"] Jakob, Jakob ; Zscheischler, Dominik Janzing, Bernhard Scholkopf","year":"2010","venue":"IEEE Transactions on Information Theory","doi":null,"url":"https://webdav.tuebingen.mpg.de/cause-effect/","internal_url":null},{"position":10,"raw":"[Kar et al., 2011] Muhsin Kar, S ¸aban Nazlıoglu, and Hüseyin Agır. Financial development and economic growth nexus in the MENA countries: Bootstrap panel granger causality analysis. Economic modelling, 28(1):685-693, 2011.","title":"Financial development and economic growth nexus in the MENA countries: Bootstrap panel granger causality analysis","authors":"Muhsin Kar, S ¸aban Nazlıoglu, Hüseyin Agır","year":"2011","venue":"Economic modelling","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[KEGG, 1995] KEGG : Kyoto Encyclopedia of Genes and Genomes. https://www.genome.jp/kegg/, 1995.","title":"KEGG : Kyoto Encyclopedia of Genes and Genomes","authors":"Kegg","year":"1995","venue":null,"doi":null,"url":"https://www.genome.jp/kegg/","internal_url":null},{"position":12,"raw":"[Kullback and Leibler, 1951] Solomon Kullback and Richard A. Leibler. On information and sufficiency. The annals of mathe- matical statistics, 22(1):79-86, 1951.","title":"On information and sufficiency","authors":"Kullback, Leibler ;, Richard A Leibler","year":"1951","venue":"The annals of mathematical statistics","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lopez-Paz et al., 2015] David Lopez-Paz, Krikamol Muandet, Bernhard Schölkopf, and Ilya Tolstikhin. Towards a learning the- ory of cause-effect inference. In ICML, pages 1452-1461, 2015.","title":"Towards a learning theory of cause-effect inference","authors":"David Lopez-Paz, Krikamol Muandet, Bernhard Schölkopf, Ilya Tolstikhin","year":"2015","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Lopez-Paz et al., 2017] David Lopez-Paz, Robert Nishihara, Soumith Chintala, Bernhard Schölkopf, and Léon Bottou. Discovering Causal Signals in Images. In CVPR, 2017.","title":"Discovering Causal Signals in Images","authors":"David Lopez-Paz, Robert Nishihara, Soumith Chintala, Bernhard Schölkopf, Léon Bottou","year":"2017","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Marinazzo et al., 2008] Daniele Marinazzo, Mario Pellicoro, and Sebastiano Stramaglia. Kernel-Granger causality and the analysis of dynamical networks. Physical Review E, 77(5):056215, 2008.","title":"Kernel-Granger causality and the analysis of dynamical networks","authors":"Daniele Marinazzo, Mario Pellicoro, Sebastiano Stramaglia","year":"2008","venue":"Physical Review E","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Muandet et al., 2017] Krikamol Muandet, Kenji Fukumizu, Bharath Sriperumbudur, Bernhard Schölkopf, et al. Kernel mean embedding of distributions: A review and beyond. Foundations and Trends R in Machine Learning, 10(1-2):1-141, 2017.","title":"Kernel mean embedding of distributions: A review and beyond","authors":"Muandet","year":"2017","venue":"Foundations and Trends R in Machine Learning","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Rahimi and Recht, 2007] Ali Rahimi and Benjamin Recht. Ran- dom features for large-scale kernel machines. In NIPS, pages 1177-1184, 2007.","title":"Random features for large-scale kernel machines","authors":"Recht Rahimi, Ali Rahimi, Benjamin Recht","year":"2007","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Scholkopf and Smola, 2001] Bernhard Scholkopf and Alexan- der J. Smola. Learning with kernels: support vector machines, regularization, optimization, and beyond. MIT press, 2001.","title":"Learning with kernels: support vector machines, regularization, optimization, and beyond","authors":"Smola Scholkopf, J Smola","year":"2001","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Schreiber, 2000] Thomas Schreiber. Measuring information trans- fer. Physical review letters, 85(2):461, 2000.","title":"Measuring information transfer","authors":"Thomas Schreiber","year":"2000","venue":"Physical review letters","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Spellman et al., 1998] Paul T. Spellman, Gavin Sherlock, Michael Q. Zhang, Vishwanath R. Iyer, Kirk Anders, Michael B. Eisen, Patrick O. Brown, David Botstein, and Bruce Futcher. Comprehensive identification of cell cycle-regulated genes of the yeast Saccharomyces cerevisiae by microarray hybridization. Molecular biology of the cell, 9(12):3273-3297, 1998.","title":"Comprehensive identification of cell cycle-regulated genes of the yeast Saccharomyces cerevisiae by microarray hybridization","authors":"T Paul, Gavin Spellman, Michael Q Sherlock, Zhang, R Vishwanath, Kirk Iyer, Michael B Anders, Patrick O Eisen, David Brown, Bruce Botstein, Futcher","year":"1998","venue":"Molecular biology of the cell","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Sriperumbudur et al., 2010] Bharath K. Sriperumbudur, Arthur Gretton, Kenji Fukumizu, Bernhard Schölkopf, and Gert R.G. Lanckriet. Hilbert space embeddings and metrics on probability measures. JMLR, 11:1517-1561, 2010.","title":"Hilbert space embeddings and metrics on probability measures","authors":"K Bharath, Arthur Sriperumbudur, Kenji Gretton, Bernhard Fukumizu, Gert R G Schölkopf, Lanckriet","year":"2010","venue":"JMLR","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Sun, 2008] Xiaohai Sun. Assessing nonlinear Granger causal- ity from multivariate time series. In ECML, pages 440-455. Springer, 2008.","title":"Assessing nonlinear Granger causality from multivariate time series","authors":"Xiaohai Sun, Sun","year":"2008","venue":"ECML","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Yao et al., 2015] Shun Yao, Shinjae Yoo, and Dantong Yu. Prior knowledge driven Granger causality analysis on gene regulatory network discovery. BMC bioinformatics, 16(1):273, 2015.","title":"Prior knowledge driven Granger causality analysis on gene regulatory network discovery","authors":"Yao","year":"2015","venue":"BMC bioinformatics","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zhu et al., 2014] Pingping Zhu, Badong Chen, and Jose C. Principe. Learning nonlinear generative models of time series with a Kalman filter in RKHS. IEEE Transactions on Signal Processing, 62(1):141-155, 2014.","title":"Learning nonlinear generative models of time series with a Kalman filter in RKHS","authors":"Pingping Zhu, Badong Chen, Jose C Principe","year":"2014","venue":"IEEE Transactions on Signal Processing","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}