Developing Data-Conscious Deep Learning Models for Product Classification
Source abstract
Abstract
In online commerce systems that trade in many products, it is important to classify the products accurately according to the product description. As may be expected, the recent advances in deep learning technologies have been applied to automatic product classification. The efficiency of a deep learning model depends on the training data and the appropriateness of the learning model for the data domain. This is also applicable to deep learning models for automatic product classification. In this study, we propose deep learning models that are conscious of input data comprising text-based product information. Our approaches exploit two well-known deep learning models and integrate them with the processes of input data selection, transformation, and filtering. We demonstrate the practicality of these models through experiments using actual product information data. The experimental results show that the models that systematically consider the input data may differ in accuracy by approximately 30% from those that do not. This study indicates that input data should be sufficiently considered in the development of deep learning models for product classification.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Text and Document Classification Technologies · Advanced Text Analysis Techniques · Web Data Mining and Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Applied Bigdata Research Center, Sookmyung Women’s University, Seoul 04310, Korea
Department of Consumer Economics, Sookmyung Women’s University, Seoul 04310, Korea
Department of Computer Science, Sookmyung Women’s University, Seoul 04310, Korea
Funding
National Research Foundation of Korea
References (23)
Show source-provided references
1. Das, P., Xia, Y., Levine, A., di Fabbrizio, G., and Datta, A. (2016, January 5–8). Large-scale taxonomy categorization for noisy product listings. Proceedings of the 2016 IEEE International Conference on Big Data (Big Data), Washington, DC, USA.10.1109/BigData.2016.7841063 ↗
2. Skinner, M. (2018). Product categorization with LSTMs and balanced pooling views. eCOM@ SIGIR, Available online: https://sigir-ecom.github.io/ecom2018/accepted-papers.html.
3. Krishnan, A., and Amarthaluri, A. (2019). Large Scale Product Categorization using Structured and Unstructured Attributes. arXiv.
4. Xia, Y., Levine, A., Das, P., di Fabbrizio, G., Shinzato, K., and Datta, A. (2017, January 3–7). Large-scale categorization of Japanese product titles using neural attention models. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, Valencia, Spain.10.18653/v1/E17-2105 ↗
5. Kim, Y. (2021). Automatic Product Category Classification Using Deep Learning. [Master’s Dissertation, Department of Computer Science, Sookmyung Women University].
6. Kim, Y. (2014). Convolutional Neural Networks for Sentence Classification. arXiv.10.3115/v1/D14-1181 ↗
7. Imagenet classification with deep convolutional neural networks10.1145/3065386 ↗
8. Yu, W., Sun, Z., Liu, H., Li, Z., and Zheng, Z. (2018). Multi-level Deep Learning based E-commerce Product Categorization. eCOM@ SIGIR, Available online: https://sigir-ecom.github.io/ecom2018/accepted-papers.html.
9. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
10. Long Short-term memory recurrent neural network architecture for large scale acoustic modeling
11. The study of Korean stopwords list for text mining
12. Empirical Study on Analyzing Training Data for CNN-based Product Classification Deep Learning Model
13. Automatic Text Classification: A Technical Review
14. Lightweight Methods for Large-Scale Product Categorization10.1002/asi.21586 ↗
15. Shen, D., Ruvini, J.-D., and Sarwar, B. (November, January 29). Large-scale item categorization for e-commerce. Proceedings of the 21st ACM International Conference on Information and Knowledge Management (CIKM’12), Maui, HI, USA.
16. Automated product taxonomy mapping in an e-commerce environment10.1016/j.eswa.2014.09.032 ↗
17. Building an Operational Product Ontology System10.1016/j.elerap.2005.08.005 ↗
18. Greedy function approximation: A gradient boosting machine10.1214/aos/1013203451 ↗
19. A machine learning approach for product matching and categorization10.3233/SW-180300 ↗
20. Ha, J., Pyo, H., and Kim, J. (2016, January 13–17). Large-scale item categorization in e-commerce using multiple recurrent neural networks. Proceedings of the 22nd ACM SIGKDD, International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.10.1145/2939672.2939678 ↗
21. Zahavy, T., Krishnan, A., Magnani, A., and Mannor, D. (2018, January 2–7). Is a Picture Worth a Thousand Words? A Deep Multi-Modal Architecture for Product Classification in E-Commerce. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.10.1609/aaai.v32i1.11419 ↗
22. Research paper classification systems based on TF-IDF and LDA schemes10.1186/s13673-019-0192-7 ↗
23. Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network10.1016/j.physd.2019.132306 ↗