# Deep Hierarchical Classification for Category Prediction in E-commerce System

arXiv: https://arxiv.org/abs/2005.06692 · HTML: https://mlsanity.com/paper/2005.06692/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 May 2020.

## Built on by (most cited first, 8 of 8)

- [WDC Products: A Multi-Dimensional Entity Matching Benchmark](https://mlsanity.com/paper/2301.09521/) (2023)
- [AMCAD: Adaptive Mixed-Curvature Representation based Advertisement Retrieval System](https://mlsanity.com/paper/2203.14683/) (2022)
- [Robust Product Classification with Instance-Dependent Noise](https://mlsanity.com/paper/2209.06946/) (2022)
- [Hierarchical Material Recognition from Local Appearance](https://mlsanity.com/paper/2505.22911/) (2025)
- [Informed deep hierarchical classification: a non-standard analysis inspired approach](https://mlsanity.com/paper/2409.16956/) (2024)
- [GSID: Generative Semantic Indexing for E-Commerce Product Understanding](https://mlsanity.com/paper/2509.23860/) (2025)
- [Hierarchical Deep Learning for Intention Estimation of Teleoperation Manipulation in Assembly Tasks](https://mlsanity.com/paper/2403.19770/) (2024)
- [Sanitize Your Responses: Mitigating Privacy Leakage in Large Language Models](https://mlsanity.com/paper/2509.24488/) (2025)

## Abstract (arXiv)

In e-commerce system, category prediction is to automatically predict categories of given texts. Different from traditional classification where there are no relations between classes, category prediction is reckoned as a standard hierarchical classification problem since categories are usually organized as a hierarchical tree. In this paper, we address hierarchical category prediction. We propose a Deep Hierarchical Classification framework, which incorporates the multi-scale hierarchical information in neural networks and introduces a representation sharing strategy according to the category tree. We also define a novel combined loss function to punish hierarchical prediction losses. The evaluation shows that the proposed approach outperforms existing approaches in accuracy.