Classifying multi-level product categories using dynamic masking and transformer models

• Published in: Journal of data, information and management (Online) information and management (Online), 2022-03, Vol.4 (1), p.71-85
• Main Authors: Ozyegen, Ozan, Jahanshahi, Hadi, Cevik, Mucahit, Bulut, Beste, Yigit, Deniz, Gonen, Fahrettin F., Başar, Ayşe
• Format: Article
• Language: English
• Subjects: Algorithms; Automation; Beverages; Brand names; Categories; Classification; Datasets; Deep learning; Electronic commerce; Machine learning; Masking; Natural language; Original; Performance prediction; Tea; Text categorization; Transformers
• ISSN: 2524-6356; 2524-6364
• DOI: 10.1007/s42488-022-00066-6

In an online shopping platform, a detailed categorization of the products greatly enhances user navigation. Online retailers also benefit from well-defined product categories as various sales and marketing operations such as special discounts and promotions can be easily done over a set of product categories. Furthermore, incorrect and subjective product categories suggested by an operator can be more easily identified thanks to an automated classification system. In this study, we investigate the task of classifying grocery product categories using product titles. We employ a wide variety of text classification models for this task, including traditional machine learning and deep learning models as well as state-of-the-art transformer models. In our analysis, we specifically focus on the generalizability of the trained classification models to the products of other online retailers, the dynamic masking of infeasible subcategories for pretrained language models, and the impact of incorporating different word embeddings. We observe that the deep learning models and the transformers significantly outperform traditional text classification methods such as XGBoost and SVM, and achieve excellent prediction performance exceeding 90% accuracy and F1-score values. We lastly explore the failure cases where a product is misclassified, and make recommendations for future studies to improve the prediction performance.