A deep neural network based product metadata validation approach for online marketplaces

Date

2023-4-19

Author

Alataş, Şükrü

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

259
views

126
downloads

Cite This

As e-commerce has become increasingly popular during the pandemic, online marketplaces have seen a surge in merchants offering various products. A critical factor in the success of these marketplaces is the user experience they provide, largely dependent on features like efficient product search, fast filtering, and attractive product images. However, maintaining the data quality of product metadata and images can be challenging, especially as the number of products grows exponentially. To address this issue, this research proposes a novel approach using an AI-based automated image validation model for validating product images and an AI-based classification model to validate product metadata in an automated fashion. Our approach offers several advantages over traditional methods, including handling complex and noisy data and adapting to various challenging product categories, such as fashion items. We demonstrate the effectiveness of this approach through comparisons with traditional methods and in different settings, ultimately showing strong support for the use of AI in product metadata validation for online marketplaces.

Subject Keywords

Metadata validation, Deep neural networks, CNN, Online marketplaces

URI

https://hdl.handle.net/11511/103101

Collections

Graduate School of Informatics, Thesis