Towards Classifying HTML-embedded Product Data Based On Machine Learning Approach

Скорочена інформація про документ
dc.contributor.authorMatveiev, Oleksandren
dc.contributor.authorZubenko, Anastasiiaen
dc.contributor.authorYevtushenko, Dmitryen
dc.contributor.authorCherednichenko, Olgaen
dc.date.accessioned2023-03-04T11:46:48Z
dc.date.available2023-03-04T11:46:48Z
dc.date.issued2021
dc.description.abstractIn this paper we explored machine learning approaches using descriptions and titles to classify footwear by brand. The provided data were taken from many different online stores. In particular, we have created a pipeline that automatically classifies product brands based on the provided data. The dataset is provided in JSON format and contains more than 40,000 rows. The categorization component was implemented using K-Nearest Neighbour (K-NN) and Support Vector Machine (SVM) algorithms. The results of the pipeline construction were evaluated basing on the classification report, especially the Precision weighted average value was considered during the calculation, which reached 79.0% for SVM and 72.0% for K-NN.en
dc.identifier.citationTowards Classifying HTML-embedded Product Data Based On Machine Learning Approach [Electronic resource] / O. Matveiev [et al.] // Modern Machine Learning Technologies and Data Science (MoMLeT+DS 2021) : proc. of the 3rd Intern. Workshop, June 5, 2021. Vol. 2917. – Electronic text data. – Lviv-Shatsk, 2021. – 11 p. – Access mode: https://ceur-ws.org/Vol-2917/paper8.pdf, free (date of the application 04.03.2023.).en
dc.identifier.orcidhttps://orcid.org/0000-0001-5907-3771
dc.identifier.orcidhttps://orcid.org/0000-0001-9178-0847
dc.identifier.orcidhttps://orcid.org/0000-0001-6250-4616
dc.identifier.orcidhttps://orcid.org/0000-0002-9391-5220
dc.identifier.urihttps://repository.kpi.kharkov.ua/handle/KhPI-Press/63001
dc.language.isoen
dc.subjectproduct classificationen
dc.subjectSVMen
dc.subjectK-Nearest Neighbouren
dc.subjectTF-IDFen
dc.subjectmachine learningen
dc.subjectvectorizationen
dc.subjectitem matchingen
dc.titleTowards Classifying HTML-embedded Product Data Based On Machine Learning Approachen
dc.typeThesisen

Файли

Контейнер файлів
Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
Matveiev_Towards_2021.pdf
Розмір:
1.69 MB
Формат:
Adobe Portable Document Format
Опис:
Завантажити
Ліцензійна угода
Зараз показуємо 1 - 1 з 1
Ескіз недоступний
Назва:
license.txt
Розмір:
11.25 KB
Формат:
Item-specific license agreed upon to submission
Опис:
Завантажити

Зібрання

Кафедра "Програмна інженерія та інтелектуальні технології управління ім. А. В. Дабагяна"