A Study on Multiple Tasks for e-Commerce Marketplaces

Authors

  • Cristian Cardellino Mercado Libre
  • Rafael Carrascosa Mercado Libre

DOI:

https://doi.org/10.32473/flairs.v34i1.128469

Keywords:

Natural Language Processing, Deep Learning, Machine Learning in Industry

Abstract

In an e-Commerce marketplace, there are multiple tasks that need to be addressed in a day-to-day basis. Some tasks such as product recommendations and product search take a fundamental role in the overall experience a user has on the site. There are however a multitude of lesser known tasks which are also relevant for the business and that need to be addressed with a comparatively smaller investment in teams and quality datasets. Examples of such tasks are the detection of counterfeit or forbidden items, the estimation of package sizes, etc. In this work we study a set of different baseline models and how they work across different tasks that come from real world data.

Downloads

Published

2021-04-18

How to Cite

Cardellino, C., & Carrascosa, R. (2021). A Study on Multiple Tasks for e-Commerce Marketplaces. The International FLAIRS Conference Proceedings, 34. https://doi.org/10.32473/flairs.v34i1.128469

Issue

Section

Special Track: Applied Natural Language Processing