{"type":"ScholarlyArticle","title":"A Gradient-Based Split Criterion for Highly Accurate and Transparent Model Trees","authors":[{"name":"Klaus Broelemann","slug":"klaus-broelemann","given":"Klaus","family":"Broelemann","affiliation":"SCHUFA Holding AG , Wiesbaden , Germany"},{"name":"Gjergji Kasneci","slug":"gjergji-kasneci","given":"Gjergji","family":"Kasneci","affiliation":"SCHUFA Holding AG , Wiesbaden , Germany"}],"abstract":"Machine learning algorithms aim at minimizing the number of false decisions and increasing the accuracy of predictions. However, the high predictive power of advanced algorithms comes at the costs of transparency. State-of-the-art methods, such as neural networks and ensemble methods, result in highly complex models with little transparency. \r\nWe propose shallow model trees as a way to combine simple and highly transparent predictive models for higher predictive power without losing the transparency of the original models. We present a novel split criterion for model trees that allows for significantly higher predictive power than state-of-the-art model trees while maintaining the same level of simplicity. This novel approach finds split points which allow the underlying simple models to make better predictions on the corresponding data. In addition, we introduce multiple mechanisms to increase the transparency of the resulting trees.","doi":"10.24963/ijcai.2019/281","url":"https://ijcai.org/proceedings/2019/281","pdf":"https://ijcai.org/proceedings/2019/0281.pdf","markdown":"https://ijcai.org/proceedings/2019/281.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/281","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Machine Learning A-L","track":"Main track","number":281,"pages":{"first":2030,"last":2037},"keywords":["Machine Learning: Classification","Machine Learning: Interpretability","Machine Learning: Explainable Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Altmann et al., 2010] André Altmann, Laura Tolos ¸i, Oliver Sander, and Thomas Lengauer. Permutation importance: a corrected feature importance measure. Bioinformatics, 26(10):1340-1347, 2010.","title":"Permutation importance: a corrected feature importance measure","authors":"Altmann","year":"2010","venue":"Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bach et al., 2015] Sebastian Bach, Alexander Binder, Grégoire Montavon, Frederick Klauschen, Klaus-Robert Müller, and Wojciech Samek. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PloS one, 10(7), 2015.","title":"On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation","authors":"Sebastian Bach, Alexander Binder, Grégoire Montavon, Frederick Klauschen, Klaus-Robert Müller, Wojciech Samek","year":"2015","venue":"PloS one","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bastani et al., 2017] Osbert Bastani, Carolyn Kim, and Hamsa Bastani. Interpretability via model extraction. arXiv preprint arXiv:1706.09773, 2017.","title":"Interpretability via model extraction","authors":"Osbert Bastani, Carolyn Kim, Hamsa Bastani","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Breiman, 2001] Leo Breiman. Random forests. Machine learning, 45(1):5-32, 2001.","title":"Leo Breiman. Random forests","authors":"Breiman","year":"2001","venue":"Machine learning","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen and Guestrin, 2016] Tianqi Chen and Carlos Guestrin. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowl- edge discovery and data mining, pages 785-794. ACM, 2016.","title":"Xgboost: A scalable tree boosting system","authors":"Tianqi Chen, Carlos Guestrin","year":"2016","venue":"Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Craven and Shavlik, 1996] Mark Craven and Jude W Shav- lik. Extracting tree-structured representations of trained networks. In Advances in neural information processing systems, pages 24-30, 1996.","title":"Extracting tree-structured representations of trained networks","authors":"Shavlik Craven, Mark Craven, Jude W Shavlik","year":"1996","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dancey et al., 2007] Darren Dancey, Zuhair A Bandar, and David McLean. Logistic model tree extraction from ar- tificial neural networks. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 37(4):794- 802, 2007.","title":"Logistic model tree extraction from artificial neural networks","authors":"Darren Dancey, Zuhair A Bandar, David Mclean","year":"2007","venue":"IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Du et al., 2018] Mengnan Du, Ninghao Liu, and Xia Hu. Techniques for interpretable machine learning. arXiv preprint arXiv:1808.00033, 2018.","title":"Techniques for interpretable machine learning","authors":"Du","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Fong and Vedaldi, 2017] Ruth C Fong and Andrea Vedaldi. Interpretable explanations of black boxes by meaningful perturbation. In Proceedings of the IEEE International Conference on Computer Vision, pages 3429-3437, 2017.","title":"Interpretable explanations of black boxes by meaningful perturbation","authors":"C Ruth, Andrea Fong, Vedaldi","year":"2017","venue":"Proceedings of the IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Freitas, 2014] Alex A Freitas. Comprehensible classifica- tion models: a position paper. ACM SIGKDD explorations newsletter, 15(1):1-10, 2014.","title":"Comprehensible classification models: a position paper","authors":"Alex A Freitas","year":"2014","venue":"ACM SIGKDD explorations newsletter","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Guidotti et al., 2018] Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Franco Turini, Fosca Giannotti, and Dino Pedreschi. A survey of methods for explaining black box models. ACM computing surveys (CSUR), 51(5):93, 2018.","title":"A survey of methods for explaining black box models","authors":"Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Franco Turini, Fosca Giannotti, Dino Pedreschi","year":"2018","venue":"ACM computing surveys","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Hastie et al., 2009] Trevor Hastie, Robert Tibshirani, and Jerome Friedman. The Elements of Statistical Learning. Springer New York, 2009.","title":"The Elements of Statistical Learning","authors":"Trevor Hastie, Robert Tibshirani, Jerome Friedman","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Jordan and Jacobs, 1994] Michael I Jordan and Robert A Jacobs. Hierarchical mixtures of experts and the em al- gorithm. Neural computation, 6(2):181-214, 1994.","title":"Hierarchical mixtures of experts and the em algorithm","authors":"I Michael, Robert A Jordan, Jacobs","year":"1994","venue":"Neural computation","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kasneci and Gottron, 2016] Gjergji Kasneci and Thomas Gottron. Licon: A linear weighting scheme for the contri- bution ofinput variables in deep artificial neural networks. In Proceedings of the 25th ACM International on Confer- ence on Information and Knowledge Management, pages 45-54. ACM, 2016.","title":"Licon: A linear weighting scheme for the contribution ofinput variables in deep artificial neural networks","authors":"Gottron Kasneci, Gjergji Kasneci, Thomas Gottron","year":"2016","venue":"Proceedings of the 25th ACM International on Conference on Information and Knowledge Management","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Landwehr et al., 2005] Niels Landwehr, Mark A. Hall, and Eibe Frank. Logistic model trees. Machine Learning, 59(1-2):161-205, 2005.","title":"Logistic model trees","authors":"Landwehr","year":"2005","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lundberg and Lee, 2017] Scott M Lundberg and Su-In Lee. A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems, pages 4765-4774, 2017.","title":"A unified approach to interpreting model predictions","authors":"M Scott, Su-In Lundberg, Lee","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Potts and Sammut, 2005] Duncan Potts and Claude Sam- mut. Incremental learning of linear model trees. Machine Learning, 61(1-3):5-48, 2005.","title":"Duncan Potts and Claude Sammut. Incremental learning of linear model trees","authors":"Sammut Potts","year":"2005","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Quinlan and others, 1992] John Ross Quinlan et al. Learn- ing with continuous classes. In 5th Australian joint confer- ence on artificial intelligence, volume 92, pages 343-348. World Scientific, 1992.","title":"Learning with continuous classes","authors":"John Ross, Quinlan","year":"1992","venue":"5th Australian joint conference on artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Quinlan, 1993] John Ross Quinlan. C4. 5: programs for machine learning. Morgan Kaufmann Publishers, 1993.","title":"C4. 5: programs for machine learning","authors":"John Ross, Quinlan","year":"1993","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Robnik-Šikonja and Kononenko, 2008] Marko Robnik- Šikonja and Igor Kononenko. Explaining classifications for individual instances. IEEE Transactions on Knowledge and Data Engineering, 20(5):589-600, May 2008.","title":"Explaining classifications for individual instances","authors":"Marko Robnik, -Šikonja, Igor Kononenko","year":"2008","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Safavian and Landgrebe, 1991] S. Rasoul Safavian and David Landgrebe. A survey of decision tree classifier methodology. IEEE transactions on systems, man, and cybernetics, 21(3):660-674, 1991.","title":"A survey of decision tree classifier methodology","authors":"S, Rasoul Safavian, David Landgrebe","year":"1991","venue":"IEEE transactions on systems, man, and cybernetics","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Schmitz et al., 1999] Gregor PJ Schmitz, Chris Aldrich, and Francois S Gouws. Ann-dt: an algorithm for extraction of decision trees from artificial neural networks. IEEE Trans- actions on Neural Networks, 10(6):1392-1401, 1999.","title":"Ann-dt: an algorithm for extraction of decision trees from artificial neural networks","authors":"P J Gregor, Chris Schmitz, Francois S Aldrich, Gouws","year":"1999","venue":"IEEE Transactions on Neural Networks","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Sokolovska et al., 2018] Nataliya Sokolovska, Yann Cheva- leyre, and Jean-Daniel Zucker. A provable algorithm for learning interpretable scoring systems. In International Conference on Artificial Intelligence and Statistics, pages 566-574, 2018.","title":"A provable algorithm for learning interpretable scoring systems","authors":"Nataliya Sokolovska, Yann Chevaleyre, Jean-Daniel Zucker","year":"2018","venue":"International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Vandewiele et al., 2016] Gilles Vandewiele, Olivier Janssens, Femke Ongenae, Filip De Turck, and Sofie Van Hoecke. Genesim: genetic extraction of a single, interpretable model. arXiv preprint arXiv:1611.05722, 2016.","title":"Genesim: genetic extraction of a single, interpretable model","authors":"Gilles Vandewiele, Olivier Janssens, Femke Ongenae, Filip De Turck, Sofie Van Hoecke","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Veale et al., 2018] Michael Veale, Max Van Kleek, and Reuben Binns. Fairness and accountability design needs for algorithmic support in high-stakes public sector decision-making. In Proceedings of the 2018 CHI Confer- ence on Human Factors in Computing Systems, CHI '18, pages 440:1-440:14, New York, NY, USA, 2018. ACM.","title":"Fairness and accountability design needs for algorithmic support in high-stakes public sector decision-making","authors":"Michael Veale, Max Van Kleek, Reuben Binns","year":"2018","venue":"Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, CHI '18","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wang and Witten, 1997] Yong Wang and Ian H. Witten. In- duction of model trees for predicting continuous classes. In Poster papers of the 9th European Conference on Ma- chine Learning. Springer, 1997.","title":"Induction of model trees for predicting continuous classes","authors":"Yong Wang, Ian H Witten","year":"1997","venue":"Poster papers of the 9th European Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Wang et al., 2015] Jialei Wang, Ryohei Fujimaki, and Yosuke Motohashi. Trading interpretability for accuracy: Oblique treed sparse additive models. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '15, pages 1245-1254, 2015.","title":"Trading interpretability for accuracy: Oblique treed sparse additive models","authors":"Wang","year":"2015","venue":"Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '15","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Yeh and Lien, 2009] I-Cheng Yeh and Che-hui Lien. The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients. Ex- pert Systems with Applications, 36(2):2473-2480, 2009.","title":"The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients","authors":"Lien Yeh","year":"2009","venue":"Expert Systems with Applications","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhang et al., 2018] Quanshi Zhang, Ying Nian Wu, and Song-Chun Zhu. Interpretable convolutional neural net- works. In IEEE Conference on Computer Vision and Pat- tern Recognition (CVPR), volume 2, page 5, 2018.","title":"Interpretable convolutional neural networks","authors":"Quanshi Zhang, Ying Nian Wu, Song-Chun Zhu","year":"2018","venue":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zikeba et al., 2016] Maciej Zikeba, Sebastian K Tomczak, and Jakub M Tomczak. Ensemble boosted trees with syn- thetic features generation in application to bankruptcy pre- diction. Expert Systems with Applications, 2016.","title":"Ensemble boosted trees with synthetic features generation in application to bankruptcy prediction","authors":"Maciej Zikeba, Sebastian K Tomczak, Jakub M Tomczak","year":"2016","venue":"Expert Systems with Applications","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zintgraf et al., 2017] Luisa M Zintgraf, Taco S Cohen, Tameem Adel, and Max Welling. Visualizing deep neural network decisions: Prediction difference analysis. arXiv preprint arXiv:1702.04595, 2017.","title":"Visualizing deep neural network decisions: Prediction difference analysis","authors":"Luisa M Zintgraf, Tameem Taco S Cohen, Max Adel, Welling","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}