Overview of Methods and Technologies for Obtaining Knowledge About Financial Proposals
DOI:
https://doi.org/10.31861/sisiot2025.2.02012Keywords:
financial proposals, knowledge obtaining, natural language processing, machine learning, semantic analysisAbstract
In the contemporary world of digital finance and data-driven decision-making, the ability to effectively obtain, analyze and interpret knowledge about financial propositions (FPs) has become a critical challenge. FPs often contain critical information about investments, risk assessments, forecasts, and strategic intent. However, this data is not always complete and is often presented in semi-structured or unstructured forms, which limits its direct applicability. The motivation for this study is the exponential growth in both the volume and complexity of financial documentation, which requires more advanced and efficient approaches to context identification and knowledge obtaining (KO). By using natural language processing (NLP) techniques, machine learning (ML) algorithms, semantic analysis, and other innovative tools, public-private companies can increase the accuracy and efficiency of financial decision-making, ensure regulatory compliance, and minimize human error. The concept of a financial system is also formalized by defining its main components and describing it as a system with distinct properties and relationships. Such a systematic approach allows for a deeper understanding of the relationships between budgeting, forecasting and risk assessment, which is critical for obtaining the "right" knowledge. Based on the formalization of the FP, a conceptual scheme for KO about the FP is proposed, where the FP is considered as a multimodal information object from which structured knowledge is obtained using various methods. This knowledge is further used for analytical support of decision-making, but has significant limitations that require the involvement of experts and additional models. The article explores modern methods and technologies aimed at automating and improving the process of KO about such FPs, and also offers suggested directions for research in this area. Among them, it is planned to study the latest technologies and advanced approaches to further improve the automation and accuracy of KO about FPs, which will contribute to more informed and final decision-making in the financial sector.
Downloads
References
L. N. Münch, K. F. Schüttler, J. Ackermann, A. Deichsel, L. Eggeling, D. Günther et al., “Writing a research funding proposal,” [Online]. Available: https://link.springer.com/article/10.1007/s00142-024-00690-x. [Accessed: August 11, 2025].
N. Khidirov, “Methods and Mechanisms of Financing Investment Activities in Industrial Enterprises,” [Online]. Available: https://www.researchgate.net/publication/351675916_Methods_and_Mechanisms_of_Financing_Investment_Activities_in_Industrial_Enterprises. [Accessed: August 11, 2025].
A. Tobisova, A. Senova, G. Izarikova, and I. Krutakova, “Proposal of a Methodology for Assessing Financial Risks and Investment Development for Sustainability of Enterprises in Slovakia,” [Online]. Available: https://www.mdpi.com/2071-1050/14/9/5068. [Accessed: August 11, 2025].
M. Mocanu, V. D. Rusu, and A. Bibiri, “Competing for research funding: Key elements impacting the evaluation of grant proposal,” [Online]. Available: https://www.cell.com/heliyon/fulltext/S2405-8440%2824%2912046-4. [Accessed: August 11, 2025].
F. Zhang, Y. Ding, and Y. Liao, “Financial data collection based on big data intelligent processing,” [Online]. Available: https://www.researchgate.net/publication/369716116_Financial_Data_Collection_Based_on_Big_Data_Intelligent_Processing. [Accessed: August 11, 2025].
L. Wang, Y. Cheng, X. Gu, and Z. Wu, “Design and Optimization of Big Data and Machine Learning Based Risk Monitoring System in Financial Markets,” [Online]. Available: https://arxiv.org/pdf/2407.19352. [Accessed: August 11, 2025].
J. Wang, W. Ding, and X. Zhu, “Financial Analysis: Intelligent Financial Data Analysis System Based on LLM-RAG,” [Online]. Available: https://arxiv.org/pdf/2504.06279. [Accessed: August 11, 2025].
N. Schaffer, C. Drieschener, and H. Krcmar, “An Analysis of Business Model Component Interrelations,” [Online]. Available: https://www.researchgate.net/publication/342304352_An_Analysis_of_Business_Model_Component_Interrelations. [Accessed: August 11, 2025].
S. Ahmed Shaikh, “Some observations on contemporary financial proposals,” [Online]. Available: https://www.researchgate.net/publication/367598580_Some_observations_on_contemporary_financial_proposals. [Accessed: August 11, 2025].
S. Pan, S. J. Rodríguez Méndez, and K. Taylor, “A pipeline for analysing grant applications,” [Online]. Available: https://arxiv.org/pdf/2210.16843. [Accessed: August 11, 2025].
D. Millo, B. Vika, and N. Baci, “Integrating natural language processing techniques of text mining into financial system: applications and limitations,” [Online]. Available: https://arxiv.org/pdf/2412.20438. [Accessed: August 11, 2025].
S. Garcia-Mendez, F. de Arriba-Perez, A. Barros-Vila, F. J. Gonzalez-Castano, and E. Costa-Montenegro, “Automatic detection of relevant information, predictions and forecasts in financial news through topic modelling with Latent Dirichlet Allocation,” [Online]. Available: https://link.springer.com/article/10.1007/s10489-023-04452-4. [Accessed: August 11, 2025].
A. Glodd and D. Hristova, “Extraction of Forward-looking Financial Information for Stock Price Prediction from Annual Reports Using NLP Techniques,” [Online]. Available: https://scholarspace.manoa.hawaii.edu/server/api/core/bitstreams/757da8dd-90c7-489f-995a-1cb29b4c9557/content. [Accessed: August 11, 2025].
Z. Hong, L. Ward, K. Chard, B. Blaiszik, and I. Foster, “Challenges and Advances in Information Extraction From Scientific Literature: A Review,” [Online]. Available: https://www.osti.gov/servlets/purl/1869908. [Accessed: August 11, 2025].
Y. Yang, Z. Wu, Y. Yang, S. Lian, F. Guo, and Z. Wang, “A Survey of Information Extraction Based on Deep Learning,” [Online]. Available: https://www.mdpi.com/2076-3417/12/19/9691. [Accessed: August 11, 2025].
A. R. Hazourli, “FinancialBERT - A Pretrained Language Model for Financial Text Mining,” [Online]. Available: https://www.researchgate.net/publication/358284785_FinancialBERT_-_A_Pretrained_Language_Model_for_Financial_Text_Mining. [Accessed: August 11, 2025].
S. A. Farimani, M. V. Jahan, and A. M. Fard, “From Text Representation to Financial Market Prediction: A Literature Review,” [Online]. Available: https://www.mdpi.com/2078-2489/13/10/466. [Accessed: August 11, 2025].
M. Wujec, “Analysis of the Financial Information Contained in the Texts of Current Reports: A Deep Learning Approach,” [Online]. Available: https://www.mdpi.com/1911-8074/14/12/582. [Accessed: August 11, 2025].
T. Repke and R. Krestel, “Extraction and Representation of Financial Entities from Text,” [Online]. Available: https://link.springer.com/chapter/10.1007/978-3-030-66891-4_11. [Accessed: August 11, 2025].
S. F. Mohsin, S. I. Jami, S. Wasi, and M. S. Siddiqui, “An automated information extraction system from the knowledge graph based annual financial reports,” [Online]. Available: https://pmc.ncbi.nlm.nih.gov/articles/PMC11157543. [Accessed: August 11, 2025].
N. Bentabet, R. Juge, I. El Maarouf, V. Mouilleron, D. Valsamou-Stanislawski, and M. El-Haj, “The Financial Document Structure Extraction Shared task: FinToc 2020,” [Online]. Available: https://aclanthology.org/2020.fnp-1.2.pdf. [Accessed: August 11, 2025].
F. Scafoglieri, A. Monaco, G. Neccia, D. Lembo, A. Limosani, and F. Medda, “Automatic Information Extraction from Investment Product Documents,” [Online]. Available: https://ceur-ws.org/Vol-3194/paper9.pdf. [Accessed: August 11, 2025].
S. Montariol, M. Martinc, A. Pelicon, S. Pollak, B. Koloski, I. Loncarski et al., “Multi-Task Learning for Features Extraction in Financial Annual Reports,” [Online]. Available: https://www.researchgate.net/publication/367534259_Multi-task_Learning_for_Features_Extraction_in_Financial_Annual_Reports. [Accessed: August 11, 2025].
F. Pala, M. Yasin Akpınar, O. Deniz, and G. Eryigit, “ViBERTgrid BiLSTM-CRF: Multimodal Key Information Extraction from Unstructured Financial Documents,” [Online]. Available: https://arxiv.org/pdf/2409.15004. [Accessed: August 11, 2025].
Published
Issue
Section
License
Copyright (c) 2025 Security of Infocommunication Systems and Internet of Things
This work is licensed under a Creative Commons Attribution 4.0 International License.
