Тип публикации: доклад, тезисы доклада, статья из сборника материалов конференций
Конференция: International Conference: Information Technologies in Business and Industry (ITBI); Novosibirsk State Tech Univ, Novosibirsk, RUSSIA; Novosibirsk State Tech Univ, Novosibirsk, RUSSIA
Год издания: 2019
Идентификатор DOI: 10.1088/1742-6596/1333/7/072025
Аннотация: The article presents a solution for the problem of identifying duplicated ads on property selling websites. This task is formulated in the form of a classification problem: The input parameters are identified then divided into basic and non-basic, as well as a class-forming feature. It is also necessary to consider the preliminary Показать полностьюdata of processed property objects, which is necessary for proper application of the classification methods. The following is a brief review of chosen modern algorithms for solving classification problems, namely: Decision trees, artificial neural networks, logistic regression. As a result of experiments, it was revealed that Artificial neural network gives the most accurate result therefore, this algorithm is suitable for the solution of the stated problem. © Published under licence by IOP Publishing Ltd.
Журнал: Journal of Physics: Conference Series
Выпуск журнала: Vol. 1333, Is. 7
Номера страниц: 72025
ISSN журнала: 17426588
Издатель: Institute of Physics Publishing