{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T10:38:16Z","timestamp":1769164696825,"version":"3.49.0"},"reference-count":57,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2019,9,5]],"date-time":"2019-09-05T00:00:00Z","timestamp":1567641600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"crossref","award":["61751306"],"award-info":[{"award-number":["61751306"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Key R8D Program of China","award":["2018YFB1004300"],"award-info":[{"award-number":["2018YFB1004300"]}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2019,9,30]]},"abstract":"<jats:p>Internet companies are facing the need for handling large-scale machine learning applications on a daily basis and distributed implementation of machine learning algorithms which can handle extra-large-scale tasks with great performance is widely needed. Deep forest is a recently proposed deep learning framework which uses tree ensembles as its building blocks and it has achieved highly competitive results on various domains of tasks. However, it has not been tested on extremely large-scale tasks. In this work, based on our parameter server system, we developed the distributed version of deep forest. To meet the need for real-world tasks, many improvements are introduced to the original deep forest model, including MART (Multiple Additive Regression Tree) as base learners for efficiency and effectiveness consideration, the cost-based method for handling prevalent class-imbalanced data, MART based feature selection for high dimension data, and different evaluation metrics for automatically determining the cascade level. We tested the deep forest model on an extra-large-scale task, i.e., automatic detection of cash-out fraud, with more than 100 million training samples. Experimental results showed that the deep forest model has the best performance according to the evaluation metrics from different perspectives even with very little effort for parameter tuning. This model can block fraud transactions in a large amount of money each day. Even compared with the best-deployed model, the deep forest model can additionally bring a significant decrease in economic loss each day.<\/jats:p>","DOI":"10.1145\/3342241","type":"journal-article","created":{"date-parts":[[2019,9,5]],"date-time":"2019-09-05T12:14:48Z","timestamp":1567685688000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":41,"title":["Distributed Deep Forest and its Application to Automatic Detection of Cash-Out Fraud"],"prefix":"10.1145","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3244-1084","authenticated-orcid":false,"given":"Ya-Lin","family":"Zhang","sequence":"first","affiliation":[{"name":"Ant Financial Services Group, China"}]},{"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Ant Financial Services Group, China"}]},{"given":"Wenhao","family":"Zheng","sequence":"additional","affiliation":[{"name":"National Key Lab for Novel Software Technology, Nanjing University, China"}]},{"given":"Ji","family":"Feng","sequence":"additional","affiliation":[{"name":"National Key Lab for Novel Software Technology, Nanjing University, China"}]},{"given":"Longfei","family":"Li","sequence":"additional","affiliation":[{"name":"Ant Financial Services Group, China"}]},{"given":"Ziqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Ant Financial Services Group, China"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[{"name":"National Key Lab for Novel Software Technology, Nanjing University, China"}]},{"given":"Zhiqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ant Financial Services Group, China"}]},{"given":"Chaochao","family":"Chen","sequence":"additional","affiliation":[{"name":"Ant Financial Services Group, China"}]},{"given":"Xiaolong","family":"Li","sequence":"additional","affiliation":[{"name":"Ant Financial Services Group, China"}]},{"given":"Yuan (Alan)","family":"Qi","sequence":"additional","affiliation":[{"name":"Ant Financial Services Group, China"}]},{"given":"Zhi-Hua","family":"Zhou","sequence":"additional","affiliation":[{"name":"National Key Lab for Novel Software Technology, Nanjing University, China"}]}],"member":"320","published-online":{"date-parts":[[2019,9,5]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"2016. MIT Technology Review. Retireved from https:\/\/www.technologyreview.com\/s\/602850\/big-data-game-changer-alibabas-double-11-event-raises-the-bar-for-online-sales\/.  2016. MIT Technology Review. Retireved from https:\/\/www.technologyreview.com\/s\/602850\/big-data-game-changer-alibabas-double-11-event-raises-the-bar-for-online-sales\/."},{"key":"e_1_2_1_2_1","first-page":"993","article-title":"Latent Dirichlet allocation","author":"Blei David M.","year":"2003","unstructured":"David M. Blei , Andrew Y. Ng , and Michael I. Jordan . 2003 . Latent Dirichlet allocation . Journal of Machine Learning Research 3 , Jan (2003), 993 -- 1022 . David M. Blei, Andrew Y. Ng, and Michael I. Jordan. 2003. Latent Dirichlet allocation. Journal of Machine Learning Research 3, Jan (2003), 993--1022.","journal-title":"Journal of Machine Learning Research 3"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1018046112532"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_2_1_5_1","first-page":"23","article-title":"From Ranknet to Lambdarank to Lambdamart: An overview","volume":"11","author":"Burges Christopher J. C.","year":"2010","unstructured":"Christopher J. C. Burges . 2010 . From Ranknet to Lambdarank to Lambdamart: An overview . Learning 11 , 23 -- 581 (2010), 81. Christopher J. C. Burges. 2010. From Ranknet to Lambdarank to Lambdamart: An overview. Learning 11, 23--581 (2010), 81.","journal-title":"Learning"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/5254.809570"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541882"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2015974"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_1_10_1","volume-title":"King","author":"Clare Amanda","year":"2001","unstructured":"Amanda Clare and Ross D . King . 2001 . Knowledge discovery in multi-label phenotype data. In European Conference on Principles of Data Mining and Knowledge Discovery. Springer , 42--53. Amanda Clare and Ross D. King. 2001. Knowledge discovery in multi-label phenotype data. In European Conference on Principles of Data Mining and Knowledge Discovery. Springer, 42--53."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/2639279.2639281"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1864708.1864770"},{"key":"e_1_2_1_13_1","unstructured":"Jeffrey Dean Greg Corrado Rajat Monga Kai Chen Matthieu Devin Mark Mao Andrew Senior Paul Tucker Ke Yang Quoc V Le etal 2012. Large scale distributed deep networks. In Advances in Neural Information Processing Systems. 1223--1231.   Jeffrey Dean Greg Corrado Rajat Monga Kai Chen Matthieu Devin Mark Mao Andrew Senior Paul Tucker Ke Yang Quoc V Le et al. 2012. Large scale distributed deep networks. In Advances in Neural Information Processing Systems. 1223--1231."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(96)00034-3"},{"key":"e_1_2_1_15_1","unstructured":"Harris Drucker and Corinna Cortes. 1996. Boosting decision trees. In Advances in Neural Information Processing Systems. 479--485.   Harris Drucker and Corinna Cortes. 1996. Boosting decision trees. In Advances in Neural Information Processing Systems. 479--485."},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.10.010"},{"key":"e_1_2_1_17_1","volume-title":"Greedy function approximation: A gradient boosting machine. Annals of Statistics","author":"Friedman Jerome","year":"2001","unstructured":"Jerome Friedman . 2001. Greedy function approximation: A gradient boosting machine. Annals of Statistics ( 2001 ), 1189--1232. Jerome Friedman. 2001. Greedy function approximation: A gradient boosting machine. Annals of Statistics (2001), 1189--1232."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1016218223"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-6226-1"},{"key":"e_1_2_1_20_1","volume-title":"Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, 685--697","author":"Ghosh Aritra","unstructured":"Aritra Ghosh , Naresh Manwani , and P. S. Sastry . 2017. On the robustness of decision tree learning under label noise . In Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, 685--697 . Aritra Ghosh, Naresh Manwani, and P. S. Sastry. 2017. On the robustness of decision tree learning under label noise. In Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, 685--697."},{"key":"e_1_2_1_21_1","volume-title":"Deep Learning","author":"Goodfellow Ian","unstructured":"Ian Goodfellow , Yoshua Bengio , Aaron Courville , and Yoshua Bengio . 2016. Deep Learning . Vol. 1 . MIT Press , Cambridge . Ian Goodfellow, Yoshua Bengio, Aaron Courville, and Yoshua Bengio. 2016. Deep Learning. Vol. 1. MIT Press, Cambridge."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2648584.2648589"},{"key":"e_1_2_1_23_1","volume-title":"Sturdivant","author":"Hosmer David W.","year":"2013","unstructured":"David W. Hosmer , Jr., Stanley Lemeshow , and Rodney X . Sturdivant . 2013 . Applied Logistic Regression. Vol. 398 . John Wiley 8 Sons. David W. Hosmer, Jr., Stanley Lemeshow, and Rodney X. Sturdivant. 2013. Applied Logistic Regression. Vol. 398. John Wiley 8 Sons."},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-2002-6504"},{"key":"e_1_2_1_25_1","unstructured":"Guolin Ke Qi Meng Thomas Finley Taifeng Wang Wei Chen Weidong Ma Qiwei Ye and Tie-Yan Liu. 2017. LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems. 3149--3157.   Guolin Ke Qi Meng Thomas Finley Taifeng Wang Wei Chen Weidong Ma Qiwei Ye and Tie-Yan Liu. 2017. LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems. 3149--3157."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0933-3657(01)00077-X"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022859003006"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148265"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.5555\/1888212.1888216"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.5555\/2685048.2685095"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/2835776.2835781"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.17"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557082"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2456899"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.2007853"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2488200"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00158"},{"key":"e_1_2_1_38_1","volume-title":"Pazzani and Daniel Billsus","author":"Michael","year":"2007","unstructured":"Michael J. Pazzani and Daniel Billsus . 2007 . Content-based recommendation systems. In The Adaptive Web. Springer , 325--341. Michael J. Pazzani and Daniel Billsus. 2007. Content-based recommendation systems. In The Adaptive Web. Springer, 325--341."},{"key":"e_1_2_1_39_1","first-page":"37","article-title":"Evaluation: From Precision, Recall and F-Measure to ROC","volume":"2","author":"Powers David Martin","year":"2011","unstructured":"David Martin Powers . 2011 . Evaluation: From Precision, Recall and F-Measure to ROC , Informedness, Markedness and Correlation , Vol. 2. 37 -- 63 . David Martin Powers. 2011. Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness and Correlation, Vol. 2. 37--63.","journal-title":"Informedness, Markedness and Correlation"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623651"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/1076034.1076119"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-018-7151-8"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-9449-2"},{"key":"e_1_2_1_44_1","volume-title":"Swamy","author":"Thulasiraman Krishnaiyan","year":"2011","unstructured":"Krishnaiyan Thulasiraman and Madisetti N. S . Swamy . 2011 . Graphs : Theory and Algorithms. John Wiley 8 Sons. Krishnaiyan Thulasiraman and Madisetti N. S. Swamy. 2011. Graphs: Theory and Algorithms. John Wiley 8 Sons."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.594"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80023-1"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2015.2472014"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623635"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2013.39"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3186580"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3041021.3054225"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098029"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1201\/b12207"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-018-9801-4"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172386"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwy108"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2006.17"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3342241","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3342241","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:26:01Z","timestamp":1750206361000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3342241"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,9,5]]},"references-count":57,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2019,9,30]]}},"alternative-id":["10.1145\/3342241"],"URL":"https:\/\/doi.org\/10.1145\/3342241","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,9,5]]},"assertion":[{"value":"2019-02-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-06-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-09-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}