{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T09:54:16Z","timestamp":1743069256333,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030676698"},{"type":"electronic","value":"9783030676704"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-67670-4_20","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T17:04:13Z","timestamp":1614186253000},"page":"323-338","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Why Did My Consumer Shop? Learning an Efficient Distance Metric for Retailer Transaction Data"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0908-9163","authenticated-orcid":false,"given":"Yorick","family":"Spenrath","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4027-4351","authenticated-orcid":false,"given":"Marwan","family":"Hassani","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3978-6464","authenticated-orcid":false,"given":"Boudewijn van","family":"Dongen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0756-3714","authenticated-orcid":false,"given":"Haseeb","family":"Tariq","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"issue":"1","key":"20_CR1","first-page":"51","volume":"14","author":"C Aggarwal","year":"2002","unstructured":"Aggarwal, C., Procopiuc, C., Yu, P.: Finding localized associations in market basket data. IEEE Trans. KDE 14(1), 51\u201362 (2002)","journal-title":"IEEE Trans. KDE"},{"key":"20_CR2","unstructured":"Arthur, D., Vassilvitskii, S.: K-Means++: the advantages of careful seeding. In: Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms. SODA 2007, pp. 1027\u20131035. Society for Industrial and Applied Mathematics, USA (2007)"},{"key":"20_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/978-3-642-37456-2_14","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"RJGB Campello","year":"2013","unstructured":"Campello, R.J.G.B., Moulavi, D., Sander, J.: Density-based clustering based on hierarchical density estimates. In: Pei, J., Tseng, V.S., Cao, L., Motoda, H., Xu, G. (eds.) PAKDD 2013. LNCS (LNAI), vol. 7819, pp. 160\u2013172. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-37456-2_14"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Chen, X., Fang, Y., Yang, M., Nie, F., Zhao, Z., Huang, J.Z.: PurTreeClust: a clustering algorithm for customer segmentation from massive customer transaction data. IEEE Trans. Knowl. Data Eng. 30(3), 559\u2013572 (2018)","DOI":"10.1109\/TKDE.2017.2763620"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Huang, J.Z., Luo, J.: PurTreeClust: a purchase tree clustering algorithm for large-scale customer transaction data. In: 2016 IEEE 32nd International Conference on Data Engineering (ICDE), pp. 661\u2013672, May 2016","DOI":"10.1109\/ICDE.2016.7498279"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., Peng, S., Huang, J.Z., Nie, F., Ming, Y.: Local PurTree spectral clustering for massive customer transaction data. IEEE Intell. Syst. 32(2), 37\u201344 (2017)","DOI":"10.1109\/MIS.2017.41"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Sun, W., Wang, B., Li, Z., Wang, X., Ye, Y.: Spectral clustering of customer transaction data with a two-level subspace weighting method. IEEE Trans. Cybern. 49(9), 3230\u20133241 (2019)","DOI":"10.1109\/TCYB.2018.2836804"},{"issue":"4","key":"20_CR8","doi-asserted-by":"publisher","first-page":"857","DOI":"10.2307\/2528823","volume":"27","author":"JC Gower","year":"1971","unstructured":"Gower, J.C.: A general coefficient of similarity and some of its properties. Biometrics 27(4), 857\u2013871 (1971)","journal-title":"Biometrics"},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Guha, S., Rastogi, R., Shim, K.: Rock: a robust clustering algorithm for categorical attributes. Inf. Syst. 25, 345\u2013366 (2000)","DOI":"10.1016\/S0306-4379(00)00022-3"},{"key":"20_CR10","unstructured":"Hamerly, G., Elkan, C.: Learning the k in K-means. In: Proceedings of the 16th International Conference on Neural Information Processing Systems. NIPS 2003, pp. 281\u2013288. MIT Press, Cambridge (2003)"},{"issue":"3","key":"20_CR11","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s40595-016-0086-9","volume":"4","author":"M Hassani","year":"2016","unstructured":"Hassani, M., Seidl, T.: Using internal evaluation measures to validate the quality of diverse stream clustering algorithms. Vietnam J. Comput. Sci. 4(3), 171\u2013183 (2016). https:\/\/doi.org\/10.1007\/s40595-016-0086-9","journal-title":"Vietnam J. Comput. Sci."},{"key":"20_CR12","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1007\/978-3-319-08979-9_11","volume-title":"Machine Learning and Data Mining in Pattern Recognition","author":"M Hassani","year":"2014","unstructured":"Hassani, M., Spaus, P., Seidl, T.: Adaptive multiple-resolution stream clustering. In: Perner, P. (ed.) MLDM 2014. LNCS (LNAI), vol. 8556, pp. 134\u2013148. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-08979-9_11"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Jain, A.K.: Data clustering: 50 years beyond K-means. Pattern Recogn. Lett. 31(8), 651\u2013666 (2010)","DOI":"10.1016\/j.patrec.2009.09.011"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Lam, S.K., Pitrou, A., Seibert, S.: Numba. In: Proceedings of the Second Workshop on the LLVM Compiler Infrastructure in HPC - LLVM 2015, pp. 1\u20136. ACM Press, New York (2015)","DOI":"10.1145\/2833157.2833162"},{"key":"20_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1007\/978-3-642-32498-7_26","volume-title":"Multidisciplinary Research and Practice for Information Systems","author":"K Lu","year":"2012","unstructured":"Lu, K., Furukawa, T.: Similarity of transactions for customer segmentation. In: Quirchmayr, G., Basl, J., You, I., Xu, L., Weippl, E. (eds.) CD-ARES 2012. LNCS, vol. 7465, pp. 347\u2013359. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-32498-7_26"},{"key":"20_CR16","unstructured":"Ng, A.Y., Jordan, M.I., Weiss, Y.: On spectral clustering: analysis and an algorithm. In: Proceedings of the 14th International Conference on Neural Information Processing Systems: Natural and Synthetic. NIPS 2001, pp. 849\u2013856. MIT Press, Cambridge (2001)"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Park, H.S., Jun, C.H.: A simple and fast algorithm for K-medoids clustering. Expert Syst. Appl. 36(2 PART 2), 3336\u20133341 (2009)","DOI":"10.1016\/j.eswa.2008.01.039"},{"key":"20_CR18","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"20_CR19","unstructured":"Pelleg, D., Moore, A.W.: X-Means: extending k-means with efficient estimation of the number of clusters. In: Proceedings of the Seventeenth International Conference on Machine Learning. ICML 2000, pp. 727\u2013734. Morgan Kaufmann Publishers Inc., San Francisco (2000)"},{"key":"20_CR20","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/0-387-25465-X_15","volume-title":"Data Mining and Knowledge Discovery Handbook","author":"L Rokach","year":"2005","unstructured":"Rokach, L., Maimon, O.: Clustering methods. In: Maimon, O., Rokach, L. (eds.) Data Mining and Knowledge Discovery Handbook, pp. 321\u2013352. Springer, Boston (2005). https:\/\/doi.org\/10.1007\/0-387-25465-X_15"},{"key":"20_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/978-3-030-32047-8_16","volume-title":"Similarity Search and Applications","author":"E Schubert","year":"2019","unstructured":"Schubert, E., Rousseeuw, P.J.: Faster k-medoids clustering: improving the PAM, CLARA, and CLARANS algorithms. In: Amato, G., Gennaro, C., Oria, V., Radovanovi\u0107, M. (eds.) SISAP 2019. LNCS, vol. 11807, pp. 171\u2013187. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32047-8_16"},{"issue":"4","key":"20_CR22","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1023\/A:1008202821328","volume":"11","author":"R Storn","year":"1997","unstructured":"Storn, R., Price, K.: Differential evolution - a simple and efficient heuristic for global optimization over continuous spaces. J. Global Optim. 11(4), 341\u2013359 (1997). https:\/\/doi.org\/10.1023\/A:1008202821328","journal-title":"J. Global Optim."},{"key":"20_CR23","volume-title":"Introduction to Data Mining","author":"PN Tan","year":"2005","unstructured":"Tan, P.N., Steinbach, M., Kumar, V.: Introduction to Data Mining, 1st edn. Addison-Wesley Longman Publishing Co., Inc., Boston (2005)","edition":"1"},{"key":"20_CR24","unstructured":"Virtanen, P., et al.: SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat. Methods 17, 261\u2013272 (2020)"},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Wang, K., Xu, C., Liu, B.: Clustering transactions using large items. In: Proceedings of the Eighth International Conference on Information and Knowledge Management. CIKM 1999, pp. 483\u2013490. ACM, New York (1999)","DOI":"10.1145\/319950.320054"},{"key":"20_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-540-74553-2_23","volume-title":"Data Warehousing and Knowledge Discovery","author":"MT Wang","year":"2007","unstructured":"Wang, M.T., Hsu, P.Y., Lin, K.C., Chen, S.S.: Clustering transactions with an unbalanced hierarchical product structure. In: Song, I.Y., Eder, J., Nguyen, T.M. (eds.) DaWaK 2007. LNCS, vol. 4654, pp. 251\u2013261. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-74553-2_23"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Applied Data Science and Demo Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-67670-4_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,23]],"date-time":"2025-02-23T23:07:51Z","timestamp":1740352071000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-67670-4_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030676698","9783030676704"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-67670-4_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ghent","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd2020.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"945","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"195","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"21% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4,5","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4,4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference took place virtually due to the COVID-19 pandemic","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}