A Machine Learning Approach to Industry Classification in Financial Markets

Dolphin, Rian; Smyth, Barry; Dong, Ruihai

doi:10.1007/978-3-031-26438-2_7

Cited by 6 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additional relevant references include [39][40][41][42][43][44], among others. The study [39] introduces a multimodal neural model aimed at training company embeddings.…”

Section: Related Literaturementioning

confidence: 99%

“…Additional relevant references include [39][40][41][42][43][44], among others. The study [39] introduces a multimodal neural model aimed at training company embeddings. This approach leverages the similarities found in both historical prices and financial news, enabling the model to capture nuanced relationships that exist between companies, thereby facilitating the identification of related companies.…”

Section: Related Literaturementioning

confidence: 99%

See 1 more Smart Citation

Comparative Analysis of NLP-Based Models for Company Classification

Rizinski,

Jankov,

Sankaradas

et al. 2024

Information

View full text Add to dashboard Cite

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 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.

show abstract

“…Additional relevant references include [39][40][41][42][43][44], among others. The study [39] introduces a multimodal neural model aimed at training company embeddings.…”

Section: Related Literaturementioning

confidence: 99%

Section: Related Literaturementioning

confidence: 99%

Comparative Analysis of NLP-Based Models for Company Classification

Rizinski,

Jankov,

Sankaradas

et al. 2024

Information

View full text Add to dashboard Cite

show abstract

“…Rahmawati's study revealed that social factors, environmental factors, and governance factors have a positive influence on the financial performance of non-financial sector companies [53], [54]. The study conducted by Fangfang Zhang, Ye Ding, and Yuhao Liao focused on the collection and analysis of financial data using big data technology, demonstrating the necessity and benefits of financial data collection and analysis [55].…”

Section: Rahmawatimentioning

confidence: 99%

The Impact of Data Volume and Analytical Complexity in Big Data Technology on Financial Performance Prediction in Financial Companies in Indonesia

Nurdiani,

Anas,

Afrizal

et al. 2023

account. Fin.

View full text Add to dashboard Cite

This quantitative research explores the intricate relationship between data volume, analytical complexity, and their combined impact on financial performance prediction across 25 Indonesian financial companies. This study utilizes multiple regression analysis and statistical techniques using IBM SPSS Statistics version 26 to uncover the dynamics at play. The findings show that data volume and analysis complexity have a significant and positive role in improving financial performance prediction. The symbiotic relationship between these factors underscores the importance of adopting a holistic approach to data management and analysis. The results of this study have profound implications for financial professionals, data scientists, and decision makers, as it provides a roadmap for utilizing Big Data technology for more accurate and informed decision making in the Indonesian financial sector.

show abstract

“…In recent years, learning embedding representations have led to breakthroughs in capturing semantic relationships in natural language processing [10]. However, the applications of embeddings in finance are mainly limited to applying pre-trained large language models to textual data, with very limited work on learning embeddings directly from nontextual financial data such as historical returns [11]. For example, the authors in [12][13][14] use event embeddings from financial news for stock return forecasting, [15] employ BERT in annual report texts, and [16] uses word embeddings for stock selection.…”

Section: Introductionmentioning

confidence: 99%