An empirical study of using an ensemble model in e-commerce taxonomy classification challenge

Yugang Jia, Xin Wang, Hanqing Cao, Boshu Ru, Tianzhong Yang

Research output: Contribution to journalConference articlepeer-review

3 Scopus citations

Abstract

In the Rakuten data challenge on taxonomy Classification for eCommerce - scale Product Catalogs, we propose an approach based on deep convolutional neural networks to predict product taxonomies using their descriptions. The classification performance of the proposed system is further improved with oversampling, threshold moving and error correct output coding. The best classification accuracy is obtained through ensembling multiple networks trained differently with multiple inputs comprising of various extracted features.

Original languageEnglish (US)
JournalCEUR Workshop Proceedings
Volume2319
StatePublished - 2018
Externally publishedYes
Event2018 SIGIR Workshop On eCommerce, eCom 2018 - Ann Arbor, United States
Duration: Jul 12 2018 → …

Keywords

  • Convolutional neural networks
  • Error correct output coding
  • Imbalanced classes
  • Multi-class classification
  • Word embedding

Fingerprint Dive into the research topics of 'An empirical study of using an ensemble model in e-commerce taxonomy classification challenge'. Together they form a unique fingerprint.

Cite this