Towards machine learning based text categorization in the financial domain

Frederic Voigt; Jose Alcaraz Calero; Keshav Dahal; Qi Wang; Kai Von Luck; Peer Stelldinger

Towards machine learning based text categorization in the financial domain

Frederic Voigt
, Jose Alcaraz Calero
, Keshav Dahal
, Qi Wang
, Kai Von Luck
, Peer Stelldinger

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

92 Downloads (Pure)

Abstract

Large language models (LLMs) have demonstrated remarkable success in the field of natural language processing (NLP). Despite their origins in NLP, these algorithms possess the theoretical capability to process any data type represented in an NLP-like format. In this study, we use stock data to illustrate three methodologies for processing regression data with LLMs, employing tokenization and contextualized embeddings. By leveraging the well-known LLM algorithm Bidirectional Encoder Representations from Transformers (BERT) [1], we apply quantitative stock price prediction methodologies to predict stock prices and stock price movements, showcasing the versatility and potential of LLMs in financial data analysis.

Original language	English
Title of host publication	Proceedings of the 6th International Conference on Cybernetics, Cognition and Machine Learning Applications
Publisher	IEEE
Publication status	Accepted/In press - 5 Aug 2024
Event	6th International Conference on Cybernetics, Cognition and Machine Learning Applications - Nordakademie University of Applied Sciences, Germany Duration: 19 Oct 2024 → 20 Oct 2024 https://www.intdatacon.com/

Conference

Conference	6th International Conference on Cybernetics, Cognition and Machine Learning Applications
Abbreviated title	ICCCMLA 2024
Country/Territory	Germany
Period	19/10/24 → 20/10/24
Internet address	https://www.intdatacon.com/

Keywords

finance
quantitative stock price prediction
natural language processing
stock movement prediction
fintech
machine learning
large language models

Access to Document

2024 08 05 Voigt et al Speech accepted - for PureAccepted author manuscript, 1.3 MBLicence: CC BY 4.0

Cite this

@inproceedings{c57eb8fd87564450b94032e93f1bf204,

title = "Towards machine learning based text categorization in the financial domain",

abstract = "Large language models (LLMs) have demonstrated remarkable success in the field of natural language processing (NLP). Despite their origins in NLP, these algorithms possess the theoretical capability to process any data type represented in an NLP-like format. In this study, we use stock data to illustrate three methodologies for processing regression data with LLMs, employing tokenization and contextualized embeddings. By leveraging the well-known LLM algorithm Bidirectional Encoder Representations from Transformers (BERT) [1], we apply quantitative stock price prediction methodologies to predict stock prices and stock price movements, showcasing the versatility and potential of LLMs in financial data analysis.",

keywords = "finance, quantitative stock price prediction, natural language processing, stock movement prediction, fintech, machine learning, large language models",

author = "Frederic Voigt and \{Alcaraz Calero\}, Jose and Keshav Dahal and Qi Wang and \{Von Luck\}, Kai and Peer Stelldinger",

year = "2024",

month = aug,

day = "5",

language = "English",

booktitle = "Proceedings of the 6th International Conference on Cybernetics, Cognition and Machine Learning Applications",

publisher = "IEEE",

address = "United States",

note = "6th International Conference on Cybernetics, Cognition and Machine Learning Applications, ICCCMLA 2024 ; Conference date: 19-10-2024 Through 20-10-2024",

url = "https://www.intdatacon.com/",

}

Voigt, F, Alcaraz Calero, J, Dahal, K , Wang, Q, Von Luck, K & Stelldinger, P 2024, Towards machine learning based text categorization in the financial domain. in Proceedings of the 6th International Conference on Cybernetics, Cognition and Machine Learning Applications. IEEE, 6th International Conference on Cybernetics, Cognition and Machine Learning Applications, Germany, 19/10/24.

TY - GEN

T1 - Towards machine learning based text categorization in the financial domain

AU - Voigt, Frederic

AU - Alcaraz Calero, Jose

AU - Dahal, Keshav

AU - Wang, Qi

AU - Von Luck, Kai

AU - Stelldinger, Peer

PY - 2024/8/5

Y1 - 2024/8/5

N2 - Large language models (LLMs) have demonstrated remarkable success in the field of natural language processing (NLP). Despite their origins in NLP, these algorithms possess the theoretical capability to process any data type represented in an NLP-like format. In this study, we use stock data to illustrate three methodologies for processing regression data with LLMs, employing tokenization and contextualized embeddings. By leveraging the well-known LLM algorithm Bidirectional Encoder Representations from Transformers (BERT) [1], we apply quantitative stock price prediction methodologies to predict stock prices and stock price movements, showcasing the versatility and potential of LLMs in financial data analysis.

AB - Large language models (LLMs) have demonstrated remarkable success in the field of natural language processing (NLP). Despite their origins in NLP, these algorithms possess the theoretical capability to process any data type represented in an NLP-like format. In this study, we use stock data to illustrate three methodologies for processing regression data with LLMs, employing tokenization and contextualized embeddings. By leveraging the well-known LLM algorithm Bidirectional Encoder Representations from Transformers (BERT) [1], we apply quantitative stock price prediction methodologies to predict stock prices and stock price movements, showcasing the versatility and potential of LLMs in financial data analysis.

KW - finance

KW - quantitative stock price prediction

KW - natural language processing

KW - stock movement prediction

KW - fintech

KW - machine learning

KW - large language models

M3 - Conference contribution

BT - Proceedings of the 6th International Conference on Cybernetics, Cognition and Machine Learning Applications

PB - IEEE

T2 - 6th International Conference on Cybernetics, Cognition and Machine Learning Applications

Y2 - 19 October 2024 through 20 October 2024

ER -

Towards machine learning based text categorization in the financial domain

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this