# Cross-Platform E-Commerce Product Categorization and Recategorization: A Multimodal Hierarchical Classification Approach

arXiv: https://arxiv.org/abs/2508.20013 · HTML: https://mlsanity.com/paper/2508.20013/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 33 references that are in the map.
- First posted on arXiv 27 Aug 2025.

## Builds on (most cited first, 13 of 13)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [FashionBERT: Text and Image Matching with Adaptive Loss for Cross-modal Retrieval](https://mlsanity.com/paper/2005.09801/) (2020)
- [Product Classification in E-Commerce using Distributional Semantics](https://mlsanity.com/paper/1606.06083/) (2016)
- [Is a picture worth a thousand words? A Deep Multi-Modal Fusion Architecture for Product Classification in e-commerce](https://mlsanity.com/paper/1611.09534/) (2016)
- [HiClass: a Python library for local hierarchical classification compatible with scikit-learn](https://mlsanity.com/paper/2112.06560/) (2021)
- [LLM-Based Robust Product Classification in Commerce and Compliance](https://mlsanity.com/paper/2408.05874/) (2024)
- [A Multimodal Late Fusion Model for E-Commerce Product Classification](https://mlsanity.com/paper/2008.06179/) (2020)
- [Consistent Text Categorization using Data Augmentation in e-Commerce](https://mlsanity.com/paper/2305.05402/) (2023)
- [Leveraging Taxonomy and LLMs for Improved Multimodal Hierarchical Classification](https://mlsanity.com/paper/2501.06827/) (2025)
- [Large Scale Product Categorization using Structured and Unstructured Attributes](https://mlsanity.com/paper/1903.04254/) (2019)
- [Multimodal E-Commerce Product Classification Using Hierarchical Fusion](https://mlsanity.com/paper/2207.03305/) (2022)

## Built on by (most cited first, 1 of 1)

- [OSR: Output Space Redistribution for Adaptive Label Removal in Classification Models](https://mlsanity.com/paper/2609.03972/) (2026)

## Abstract (arXiv)

This study addresses critical industrial challenges in e-commerce product categorization, namely platform heterogeneity and the structural limitations of existing taxonomies, by developing and deploying a multimodal hierarchical classification framework. Using a dataset of 271,700 products from 40 international fashion e-commerce platforms, we integrate textual features (RoBERTa), visual features (ViT), and joint vision-language representations (CLIP). We investigate fusion strategies, including early, late, and attention-based fusion within a hierarchical architecture enhanced by dynamic masking to ensure taxonomic consistency. Results show that CLIP embeddings combined via an MLP-based late-fusion strategy achieve the highest hierarchical F1 (98.59%), outperforming unimodal baselines. To address shallow or inconsistent categories, we further introduce a self-supervised "product recategorization" pipeline using SimCLR, UMAP, and cascade clustering, which discovered new, fine-grained categories (for example, subtypes of "Shoes") with cluster purities above 86%. Cross-platform experiments reveal a deployment-relevant trade-off: complex late-fusion methods maximize accuracy with diverse training data, while simpler early-fusion methods generalize more effectively to unseen platforms. Finally, we demonstrate the framework's industrial scalability through deployment in EURWEB's commercial transaction intelligence platform via a two-stage inference pipeline, combining a lightweight RoBERTa stage with a GPU-accelerated multimodal stage to balance cost and accuracy.