Кафедри

Постійне посилання на розділhttps://repository.kpi.kharkov.ua/handle/KhPI-Press/35393

Переглянути

Фільтри

20182

Налаштування

Автор: search.filters.author.Godlevskyi, Mikhail

Результати пошуку

Зараз показуємо 1 - 2 з 2
  • Ескіз
    Документ
    Towards Improving the Search Quality on the Trading Platforms
    (Springer International Publishing AG, 2018) Cherednichenko, Olga; Vovk, Maryna Anatoliivna; Kanishcheva, Olga; Godlevskyi, Mikhail
    In this paper, the problem of the search quality on the trading platforms, such AliExpress, eBay and others is explored, the major types of problems that arise in product search by customers are considered. The usage of the classical clusterization algorithms for grouping similar products according to their descriptions is studied. A data set for experimenting consists of different items (smartphones) from e-shop eBay is developed. Each entity in this corpus photos and a product description are given. These texts are used for item comparing in order to perform similar groups or similar items. The results show that the k-means algorithm is good for preliminary grouping but for detailed processing, other methods and approaches are required.
  • Ескіз
    Документ
    Studying items similarity for dependable buying on electronic marketplaces
    (2018) Cherednichenko, Olga; Vovk, Maryna Anatoliivna; Kanishcheva, Olga; Godlevskyi, Mikhail
    The processing of product buying is a very difficult task when we have thousands of items in each market category. In order to study items similarity for dependable buying we try to analyze item descriptions on AliExpress, eBay marketplaces and test k-means algorithm for item grouping/product segmentation. The usage of the classical clusterization algorithms for grouping similar products according to their descriptions is studied. A corpus of different products (bikes and smartphones) from e-shop AliExpress, eBay is developed. Each entity in this corpus contains photos and a product description. Each entity in this corpus contains product description with different fields. These short texts are used for experiments. As a result, it is found out that the k-means algorithm works well only for uniformly distributed data by categories, but this is not suitable for the segmentation of heterogeneous descriptions. The task of item descriptions systematization is set in the research below.