Ве молиме користете го овој идентификатор да го цитирате или поврзете овој запис: http://hdl.handle.net/20.500.12188/33956
Наслов: Comparative analysis of NLP-based models for company classification
Authors: Rizinski, Maryan
Jankov, Andrej
Sankaradas, Vignesh
Pinsky, Eugene
Mishkovski, Igor 
Trajanov, Dimitar 
Keywords: company classification; industry classification; natural language processing; machine learning; deep learning; finance; fintech
Issue Date: 31-јан-2024
Publisher: MDPI
Journal: Information
Abstract: The task of company classification is traditionally performed using established standards, such as the Global Industry Classification Standard (GICS). However, these approaches heavily rely on laborious manual efforts by domain experts, resulting in slow, costly, and vendor-specific assignments. Therefore, we investigate recent natural language processing (NLP) advancements to automate the company classification process. In particular, we employ and evaluate various NLP-based models, including zero-shot learning, One-vs-Rest classification, multi-class classifiers, and ChatGPT-aided classification. We conduct a comprehensive comparison among these models to assess their effectiveness in the company classification task. The evaluation uses the Wharton Research Data Services (WRDS) dataset, consisting of textual descriptions of publicly traded companies. Our findings reveal that the RoBERTa and One-vs-Rest classifiers surpass the other methods, achieving F1 scores of 0.81 and 0.80 on the WRDS dataset, respectively. These results demonstrate that deep learning algorithms offer the potential to automate, standardize, and continuously update classification systems in an efficient and cost-effective way. In addition, we introduce several improvements to the multi-class classification techniques: (1) in the zero-shot methodology, we use TF-IDF to enhance sector representation, yielding improved accuracy in comparison to standard zero-shot classifiers; (2) next, we use ChatGPT for dataset generation, revealing potential in scenarios where datasets of company descriptions are lacking; and (3) we also employ K-Fold to reduce noise in the WRDS dataset, followed by conducting experiments to assess the impact of noise reduction on the company classification results.
URI: http://hdl.handle.net/20.500.12188/33956
Appears in Collections:Faculty of Computer Science and Engineering: Journal Articles

Files in This Item:
File SizeFormat 
Comparative_Analysis_of_NLP_Based_Models.pdf684.17 kBAdobe PDFView/Open
Прикажи целосна запис

Google ScholarTM

Проверете


Записите во DSpace се заштитени со авторски права, со сите права задржани, освен ако не е поинаку наведено.