Muratova A., Sushko P., Espy T. Black-Box Classification Techniques for Demographic Sequences: from Customised SVM to RNN. In: Proceedings of the Fourth Workshop on Experimental Economics and Machine Learning (EEML 2017), Dresden, Germany, September 17-18, 2017 ... Muratova A., Sushko P., Espy T. Black-Box Classification Techniques for Demographic Sequences: from Customised SVM to RNN. In: Proceedings of the Fourth Workshop on Experimental Economics and Machine Learning (EEML 2017), Dresden, Germany, September 17-18, 2017 / Ed. by R. Tagiew, D. I. Ignatov, A. Hilbert, K. Heinrich, R. Delhibabu. Aachen : CEUR Workshop Proceedings, 2017. P. 31-40.ISSN 1613-0073Размещена на сайте: 14.11.17Текст статьи на сайте CEUR Workshop Proceedings (CEUR-WS.org) URL: http://ceur-ws.org/Vol-1968/paper4.pdfСсылка при цитировании:Muratova A., Sushko P., Espy T. Black-Box Classification Techniques for Demographic Sequences: from Customised SVM to RNN. In: Proceedings of the Fourth Workshop on Experimental Economics and Machine Learning (EEML 2017), Dresden, Germany, September 17-18, 2017 / Ed. by R. Tagiew, D. I. Ignatov, A. Hilbert, K. Heinrich, R. Delhibabu. Aachen : CEUR Workshop Proceedings, 2017. P. 31-40.Muratova A., Sushko P., Espy T. Black-Box Classification Techniques for Demographic Sequences: from Customised SVM to RNN. In: Proceedings of the Fourth Workshop on Experimental Economics and Machine Learning (EEML 2017), Dresden, Germany, September 17-18, 2017 / Ed. by R. Tagiew, D. I. Ignatov, A. Hilbert, K. Heinrich, R. Delhibabu. Aachen : CEUR Workshop Proceedings, 2017. P. 31-40.Авторы:Муратова А.А., Сушко П.Е., Эспи Т.Г.АннотацияNowadays there is a large amount of demographic data which should be analysed and interpreted. From accumulated demographic data, more useful information can be extracted by applying modern methods of data mining. The aim of this study is to compare the methods of classification of demographic data by customising the SVM kernels using various similarity measures. Since demographers are interested in sequences without discontinuity, formulas for such sequences similarity measures were derived. Then they were used as kernels in the SVM method, which is the novelty of this study. Recurrent neural network algorithms, such as SimpleRNN, GRU and LSTM, are also compared. The best classification result with SVM method is obtained using a special kernel function in SVM by transforming sequences into features, but recurrent neural network outperforms SVM.Ключевые слова: data mining demographics support vector machines neural networks classification sequences similarity Рубрики: Методы сбора и анализа социологических данныхВозможно, вам будут интересны другие публикации:Толстова Ю. Н.Новые информационные технологии как фактор повышения эффективности социологического исследования // Математическое моделирование социальных процессов. Сб трудов. Вып.17. М.: Экономинформ, 2015. С. 210-228Давыдов А. А.Качественные исследования: перспективы развития// Официальный сайт ИC РАН. - 2008. URL:http://www.isras.ru/publ.html?id=1128Galina G. Tatarova, Anna V. Kuchenkova. Fuzzy set QCA method for classification of countries according to the pecularities of their political culture // Differeces, Inegualities and sociological Imagination: View from Russia / Editor-in-Chef V.Mansurov, Moscow, 2015. P. 37-46. CD ROM.Ванькина И. Н., Крошилин С. В., Крошилин И.С.Возможности нейронных сетей для решения задач импортозамещения для отечественных предприятий // Региональные проблемы преобразования экономики. – 2023. – № 11(157). – С. 67-76.Rudnev M., Magun V., Schmidt P. Basic Human Values: Stability of Value Typology in Europe // Values, economic crisis and democracy. Abingdon : Routledge, 2016. Ch. 2. P. 21-49.