Proactive data mining using decision trees. Dahan, H., Maimon, O., Cohen, S., & Rokach, L. In Electrical & Electronics Engineers in Israel (IEEEI), 2012 IEEE 27th Convention of, pages 1–5, 2012. IEEE.
Link doi abstract bibtex Most of the existing data mining algorithms are #x2018;passive #x2019;. That is, they produce models which can describe patterns, but leave the decision on how to react to these patterns in the hands of the user. In contrast, in this work we describe a proactive approach to data mining, and describe an implementation of that approach, using decision trees. We show that the proactive role requires the algorithms to consider additional domain knowledge, which is exogenous to the training set. We also suggest a novel splitting criterion, termed maximalutility, which is driven by the proactive agenda.
@inproceedings{dahan2012proactive,
author = {Dahan, H. and Maimon, O. and Cohen, S. and Rokach, L.},
organization = {IEEE},
title = {Proactive data mining using decision trees},
pages = {1--5},
year = {2012},
doi = {10.1109/EEEI.2012.6377048},
ee = {http://dx.doi.org/10.1109/EEEI.2012.6377048},
booktitle = {Electrical \& Electronics Engineers in Israel (IEEEI), 2012 IEEE 27th Convention of},
abstract={Most of the existing data mining algorithms are #x2018;passive #x2019;. That is, they produce models which can describe patterns, but leave the decision on how to react to these patterns in the hands of the user. In contrast, in this work we describe a proactive approach to data mining, and describe an implementation of that approach, using decision trees. We show that the proactive role requires the algorithms to consider additional domain knowledge, which is exogenous to the training set. We also suggest a novel splitting criterion, termed maximalutility, which is driven by the proactive agenda.},
keywords = {Active learning, Cost-sensitive learning, Decision trees}
}
Downloads: 0
{"_id":"ye5B96r5KZKtyAEQk","bibbaseid":"dahan-maimon-cohen-rokach-proactivedataminingusingdecisiontrees-2012","author_short":["Dahan, H.","Maimon, O.","Cohen, S.","Rokach, L."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Dahan"],"firstnames":["H."],"suffixes":[]},{"propositions":[],"lastnames":["Maimon"],"firstnames":["O."],"suffixes":[]},{"propositions":[],"lastnames":["Cohen"],"firstnames":["S."],"suffixes":[]},{"propositions":[],"lastnames":["Rokach"],"firstnames":["L."],"suffixes":[]}],"organization":"IEEE","title":"Proactive data mining using decision trees","pages":"1–5","year":"2012","doi":"10.1109/EEEI.2012.6377048","ee":"http://dx.doi.org/10.1109/EEEI.2012.6377048","booktitle":"Electrical & Electronics Engineers in Israel (IEEEI), 2012 IEEE 27th Convention of","abstract":"Most of the existing data mining algorithms are #x2018;passive #x2019;. That is, they produce models which can describe patterns, but leave the decision on how to react to these patterns in the hands of the user. In contrast, in this work we describe a proactive approach to data mining, and describe an implementation of that approach, using decision trees. We show that the proactive role requires the algorithms to consider additional domain knowledge, which is exogenous to the training set. We also suggest a novel splitting criterion, termed maximalutility, which is driven by the proactive agenda.","keywords":"Active learning, Cost-sensitive learning, Decision trees","bibtex":"@inproceedings{dahan2012proactive,\r\n author = {Dahan, H. and Maimon, O. and Cohen, S. and Rokach, L.},\r\n organization = {IEEE},\r\n title = {Proactive data mining using decision trees},\r\n pages = {1--5},\r\n year = {2012},\r\n doi\t\t= {10.1109/EEEI.2012.6377048},\r\n ee\t\t= {http://dx.doi.org/10.1109/EEEI.2012.6377048},\r\n booktitle = {Electrical \\& Electronics Engineers in Israel (IEEEI), 2012 IEEE 27th Convention of},\r\n abstract={Most of the existing data mining algorithms are #x2018;passive #x2019;. That is, they produce models which can describe patterns, but leave the decision on how to react to these patterns in the hands of the user. In contrast, in this work we describe a proactive approach to data mining, and describe an implementation of that approach, using decision trees. We show that the proactive role requires the algorithms to consider additional domain knowledge, which is exogenous to the training set. We also suggest a novel splitting criterion, termed maximalutility, which is driven by the proactive agenda.},\r\n keywords\t= {Active learning, Cost-sensitive learning, Decision trees}\r\n}\r\n\r\n\r\n","author_short":["Dahan, H.","Maimon, O.","Cohen, S.","Rokach, L."],"key":"dahan2012proactive","id":"dahan2012proactive","bibbaseid":"dahan-maimon-cohen-rokach-proactivedataminingusingdecisiontrees-2012","role":"author","urls":{"Link":"http://dx.doi.org/10.1109/EEEI.2012.6377048"},"keyword":["Active learning","Cost-sensitive learning","Decision trees"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"www.ise.bgu.ac.il/faculty/liorr/liorrokach122012.txt","dataSources":["HLsp6sSsQQZwywcSL","NhJvHJs9CpZ5T5D7K"],"keywords":["active learning","cost-sensitive learning","decision trees"],"search_terms":["proactive","data","mining","using","decision","trees","dahan","maimon","cohen","rokach"],"title":"Proactive data mining using decision trees","year":2012}