{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T06:55:37Z","timestamp":1766732137539,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","funder":[{"name":"Engineering and Physical Sciences Research Council (EPSRC)","award":["Digital Navigation of Chemical Space (EP\/V026887\/1)"],"award-info":[{"award-number":["Digital Navigation of Chemical Space (EP\/V026887\/1)"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1145\/3773276.3774284","type":"proceedings-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T08:16:18Z","timestamp":1766564178000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Evolutionary Train-Test Split for Hierarchical Monte Carlo Ensemble"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2972-4024","authenticated-orcid":false,"given":"Ziauddin","family":"Ursani","sequence":"first","affiliation":[{"name":"University of Liverpool, Liverpool, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1893-7785","authenticated-orcid":false,"given":"Dmytro","family":"Antypov","sequence":"additional","affiliation":[{"name":"University of Liverpool, Liverpool, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5683-4106","authenticated-orcid":false,"given":"Katie","family":"Atkinson","sequence":"additional","affiliation":[{"name":"University of Liverpool, Liverpool, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4923-3003","authenticated-orcid":false,"given":"Matthew","family":"Dyer","sequence":"additional","affiliation":[{"name":"University of Liverpool, Liverpool, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1910-2483","authenticated-orcid":false,"given":"Matthew J.","family":"Rosseinsky","sequence":"additional","affiliation":[{"name":"University of Liverpool, Liverpool, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9093-9518","authenticated-orcid":false,"given":"Sven","family":"Schewe","sequence":"additional","affiliation":[{"name":"University of Liverpool, Liverpool, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6260-9477","authenticated-orcid":false,"given":"Ahsan Ahmad","family":"Ursani","sequence":"additional","affiliation":[{"name":"Mehran University of Engineering and Technology, Jamshoro, Sindh, Pakistan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6933-0628","authenticated-orcid":false,"given":"Andrij","family":"Vasylenko","sequence":"additional","affiliation":[{"name":"University of Liverpool, Liverpool, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2025,12,24]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Joaquin Abellan Carlos\u00a0J Mantas Javier\u00a0G Castellano and Seraf\u00edn Moral-Garc\u00eda. 2018. Increasing diversity in random forest learning algorithm via imprecise probabilities. Expert Systems with Applications 97 (2018) 228\u2013243.","DOI":"10.1016\/j.eswa.2017.12.029"},{"key":"e_1_3_3_1_3_2","unstructured":"Arthur Asuncion David Newman et\u00a0al. 2007. UCI machine learning repository."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Thomas Bartz-Beielstein J\u00fcrgen Branke J\u00f6rn Mehnen and Olaf Mersmann. 2014. Evolutionary algorithms. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 4 3 (2014) 178\u2013195.","DOI":"10.1002\/widm.1124"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1201\/9780203738535-10"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Dimitris Bertsimas and Jack Dunn. 2017. Optimal classification trees. Machine Learning 106 (2017) 1039\u20131082.","DOI":"10.1007\/s10994-017-5633-9"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Leo Breiman. 1996. Bagging predictors. Machine learning 24 2 (1996) 123\u2013140.","DOI":"10.1023\/A:1018054314350"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Judith Clymo Christopher\u00a0M Collins Katie Atkinson Matthew\u00a0S Dyer Michael\u00a0W Gaultois Vladimir\u00a0V Gusev Matthew\u00a0J Rosseinsky and Sven Schewe. 2025. Exploration of chemical space through automated reasoning. Angewandte Chemie 137 6 (2025) e202417657.","DOI":"10.1002\/ange.202417657"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"George\u00a0B Dantzig. 2002. Linear programming. Operations research 50 1 (2002) 42\u201347.","DOI":"10.1287\/opre.50.1.42.17798"},{"key":"e_1_3_3_1_10_2","first-page":"136","volume-title":"Proceedings of an International Conference on Genetic Algorithms and Their Applications, Carnegie-Mellon University, Pittsburgh","author":"Davis L","unstructured":"L Davis. [n. d.]. Job shop scheduling with genetic algorithms. 1985. In Proceedings of an International Conference on Genetic Algorithms and Their Applications, Carnegie-Mellon University, Pittsburgh. 136\u2013140."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"R\u00f4mulo\u00a0BP Drumond Renan\u00a0F Albuquerque Guilherme\u00a0A Barreto and Amauri\u00a0H Souza. 2022. Pattern classification based on regional models. Applied Soft Computing 129 (2022) 109592.","DOI":"10.1016\/j.asoc.2022.109592"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Alexander Dunn Qi Wang Alex Ganose Daniel Dopp and Anubhav Jain. 2020. Benchmarking materials property prediction methods: the Matbench test set and Automatminer reference algorithm. npj Computational Materials 6 1 (2020) 138.","DOI":"10.1038\/s41524-020-00406-3"},{"key":"e_1_3_3_1_13_2","first-page":"154","volume-title":"Proc. 1st Int. Conf. Genetic Algorithm, IEEE","author":"Goldberg David\u00a0E","year":"1985","unstructured":"David\u00a0E Goldberg. 1985. Loci and the traveling salesman problem. In Proc. 1st Int. Conf. Genetic Algorithm, IEEE. 154\u2013159."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"CJ Hargreaves MW Gaultois LM Daniels EJ Watts VA Kurlin M Moran Y Dang R Morris A Morscher K Thompson et\u00a0al. [n. d.]. A database of experimentally measured lithium solid electrolyte conductivities evaluated with machine learning. Npj Comput Mater. Jan. 2023; 9 (1).","DOI":"10.1038\/s41524-022-00951-z"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Saima\u00a0Sharleen Islam Md\u00a0Samiul Haque M\u00a0Saef\u00a0Ullah Miah Talha\u00a0Bin Sarwar and Ramdhan Nugraha. 2022. Application of machine learning algorithms to predict the thyroid disease risk: an experimental comparative study. PeerJ Computer Science 8 (2022) e898.","DOI":"10.7717\/peerj-cs.898"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"V\u00a0Roshan Joseph and Akhil Vakayil. 2022. SPlit: An optimal method for data splitting. Technometrics 64 2 (2022) 166\u2013176.","DOI":"10.1080\/00401706.2021.1921037"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1134\/S1064562423701600"},{"key":"e_1_3_3_1_18_2","unstructured":"Brad\u00a0L Miller David\u00a0E Goldberg et\u00a0al. 1995. Genetic algorithms tournament selection and the effects of noise. Complex systems 9 3 (1995) 193\u2013212."},{"key":"e_1_3_3_1_19_2","first-page":"224","volume-title":"Proceedings of the Second International Conference on Genetic Algorithms on Genetic algorithms and their application","author":"Oliver IM","year":"1987","unstructured":"IM Oliver, DJd Smith, and John\u00a0RC Holland. 1987. A study of permutation crossover operators on the traveling salesman problem. In Proceedings of the Second International Conference on Genetic Algorithms on Genetic algorithms and their application. 224\u2013230."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"G Pavai and TV Geetha. 2016. A survey on crossover operators. ACM Computing Surveys (CSUR) 49 4 (2016) 1\u201343.","DOI":"10.1145\/3009966"},{"key":"e_1_3_3_1_21_2","first-page":"31","volume-title":"WDS","author":"Reitermanova Zuzana","year":"2010","unstructured":"Zuzana Reitermanova et\u00a0al. 2010. Data splitting. In WDS, Vol.\u00a010. Matfyzpress Prague, 31\u201336."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Robert\u00a0E Schapire. 2003. The boosting approach to machine learning: An overview. Nonlinear estimation and classification - - (2003) 149\u2013171.","DOI":"10.1007\/978-0-387-21579-2_9"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Somayeh Shahrabadi Telmo Ad\u00e3o Emanuel Peres Raul Morais Lu\u00eds\u00a0G Magalh\u00e3es and Victor Alves. 2024. Automatic optimization of deep learning training through feature-aware-based dataset splitting. Algorithms 17 3 (2024) 106.","DOI":"10.3390\/a17030106"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEEM58616.2023.10406516"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA61862.2024.00272"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA61862.2024.00182"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIBD.2018.8396159"},{"key":"e_1_3_3_1_28_2","volume-title":"ACM Conference Proceedings","author":"Ursani Z","year":"2018","unstructured":"Z Ursani and DW Corne. 2018. A novel nonlinear discriminant classifier trained by an evolutionary algorithm. Accepted in the 10th International Conference on Machine Learning and Computing (ICMLC 2018), University of Macau, China, 26\u201328 February 2018. In ACM Conference Proceedings."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCMI.2017.8279593"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-96292-4_22"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-22999-3_54"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Ziauddin Ursani and Ahsan\u00a0Ahmad Ursani. 2023. The theory of probabilistic hierarchical learning for classification. Annals of Emerging Technologies in Computing (AETiC) 7 1 (2023) 61\u201374.","DOI":"10.33166\/AETiC.2023.01.005"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Anthony Yu-Tung Wang Steven\u00a0K Kauwe Ryan\u00a0J Murdock and Taylor\u00a0D Sparks. 2021. Compositionally restricted attention-based network for materials property predictions. Npj Computational Materials 7 1 (2021) 77.","DOI":"10.1038\/s41524-021-00545-1"}],"event":{"name":"BDCAT '25: IEEE\/ACM 12th International Conference on Big Data Computing, Applications and Technologies","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"],"location":"Nantes France","acronym":"BDCAT '25"},"container-title":["Proceedings of the IEEE\/ACM 12th International Conference on Big Data Computing, Applications and Technologies"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3773276.3774284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T06:52:28Z","timestamp":1766731948000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3773276.3774284"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":32,"alternative-id":["10.1145\/3773276.3774284","10.1145\/3773276"],"URL":"https:\/\/doi.org\/10.1145\/3773276.3774284","relation":{},"subject":[],"published":{"date-parts":[[2025,12]]},"assertion":[{"value":"2025-12-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}