A Review on Graph Neural Network Methods in Financial Applications

Wang, Jianian; Zhang, Sheng; Song, Rui

doi:10.6339/22-jds1047

Cited by 18 publications

(5 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We intend to apply this CNN architecture in other databases with similar characteristics and also compare it with other techniques, such as Graph Neural Network methods, which have recently been applied to financial data in different contexts (Li et al, 2020; Li, Wang, et al, 2022; Wang et al, 2022).…”

Section: Discussionmentioning

confidence: 99%

Convolutional neural networks applied to data organized as OLAP cubes

Caputo,

dos Santos,

da Rocha

2023

Expert Systems

View full text Add to dashboard Cite

This paper presents a Convolutional Neural Network (CNN) architecture named OlapNet, which incorporates implicit operations of OLAP cubes (or data cubes). OLAP cubes are produced from database tables or spreadsheets and they allow particular operations that support performing complex queries efficiently. OlapNet permits evaluating various combinations of these OLAP operations in its search space and thus, it enables, in part, to automate the data transformation step in the knowledge discovery process. A sample of data from an actual database containing anonymized data on the debt history of customers of a financial institution has been used to evaluate our proposal. A predictive classification problem to estimate the probability of any given customer contracting new credits in the next three months has been modelled from these data. Then, traditional methods of Machine Learning and CNN were applied. The results showed that CNN, using the OlapNet architecture, outperforms traditional methods in almost all cases, indicating that the proposed architecture is quite promising.

show abstract

Section: Discussionmentioning

confidence: 99%

Convolutional neural networks applied to data organized as OLAP cubes

Caputo,

dos Santos,

da Rocha

2023

Expert Systems

View full text Add to dashboard Cite

show abstract

“…In financial data analysis, Graph Neural Networks (GNNs) stand out for their ability to interpret the complex dynamics of financial markets. The study [27] provides a detailed overview of GNNs in finance, showcasing their effectiveness in understanding financial data's multifaceted aspects. It outlines how GNNs are applied across various financial tasks, such as predicting stock market trends, identifying loan default risks, and detecting fraudulent activities.…”

Section: Related Workmentioning

confidence: 99%

GNN Graph Classification In Action: Uncovering Patterns in Time Series Data

Romanova

2024

Preprint

View full text Add to dashboard Cite

This study pioneers a technique for analyzing time series data through Graph Neural Network (GNN) Graph Classification, extending its application from the traditional arenas of biology and chemistry to the intricate domain of time series analysis. It elaborates on the process of constructing and examining graphs derived from time series data, utilizing both single graphs and sliding window graphs. This methodology proves effective in discerning complex interrelations within the data. A critical insight from applying GNN Graph Classification to single graphs is the models’ acute sensitivity to graph structures. This attribute significantly enhances their capacity to identify outliers and decode complex patterns that hint at systemic shifts. Such sensitivity underscores the utility of GNN Graph Classification in elucidating time series data dynamics, indicating its broad potential across diverse analytical endeavors. Integrating sliding window techniques with GNN models, our approach emerges as a versatile analysis tool. It adeptly identifies temporal variations and nuanced patterns that elude traditional static analysis techniques. The findings affirm the adaptability and promise of GNN Graph Classification in conducting thorough time series analysis. By spotlighting the models’ structural sensitivity and leveraging advanced sliding window methodologies, this research broadens the application spectrum of GNN Graph Classification in data analysis. It lays the groundwork for future explorations in time series and affiliated domains. Marking a significant leap forward, this study illuminates the capacity of GNN Graph Classification models to dissect and interpret complex data patterns, paving the way for novel time series analysis applications and beyond.

show abstract

“…The Feedforward Neural Network (FNN) [7,19,[24][25][26][27][28][29] emerges as a robust artificial neural network model with notable relevance in the domain of stock selection. Typically, it consists of three or more layers, encompassing an input layer, at least one hidden layer, and an output layer.…”

Section: Feedforward Neural Network (Fnn)mentioning

confidence: 99%

“…An escalating body of research is delving into the application of graph neural networks (GNNs) within the financial realm, driven by their aptitude for capturing the intricate interconnections between stocks. A study published in 2021 [29] synthesized the typical architectures of GNNs deployed in the financial sector.…”

Section: Graph Attention Network (Gat)mentioning

confidence: 99%

Stock Selection Using Machine Learning Based on Financial Ratios

Tsai,

Gao,

Yuan

2023

Mathematics

View full text Add to dashboard Cite

Stock prediction has garnered considerable attention among investors, with a recent focus on the application of machine learning techniques to enhance predictive accuracy. Prior research has established the effectiveness of machine learning in forecasting stock market trends, irrespective of the analytical approach employed, be it technical, fundamental, or sentiment analysis. In the context of fiscal year-end selection, the decision may initially seem straightforward, with December 31 being the apparent choice, as discussed by B. Kamp in 2002. The primary argument for a uniform fiscal year-end centers around comparability. When assessing the financial performance of two firms with differing fiscal year-ends, substantial shifts in the business environment during non-overlapping periods can impede meaningful comparisons. Moreover, when two firms merge, the need to synchronize their annual reporting often results in shorter or longer fiscal years, complicating time series analysis. In the US S&P stock market, misaligned fiscal years lead to variations in report publication dates across different industries and market segments. Since the financial reporting dates of US S&P companies are determined independently by each listed entity, relying solely on these dates for investment decisions may prove less than entirely reliable and impact the accuracy of return prediction models. Hence, our interest lies in the synchronized fiscal year of the TW stock market, leveraging machine learning models for fundamental analysis to forecast returns. We employed four machine learning models: Random Forest (RF), Feedforward Neural Network (FNN), Gated Recurrent Unit (GRU), and Financial Graph Attention Network (FinGAT). We crafted portfolios by selecting stocks with higher predicted returns using these machine learning models. These portfolios outperformed the TW50 index benchmarks in the Taiwan stock market, demonstrating superior returns and portfolio scores. Our study’s findings underscore the advantages of using aligned financial ratios for predicting the top 20 high-return stocks in a mid-to-long-term investment context, delivering over 50% excess returns across the four models while maintaining lower risk profiles. Using the top 10 high-return stocks produced over 100% relative returns with an acceptable level of risk, highlighting the effectiveness of employing machine learning techniques based on financial ratios for stock prediction.

show abstract

A Review on Graph Neural Network Methods in Financial Applications

Cited by 18 publications

References 43 publications

Convolutional neural networks applied to data organized as OLAP cubes

Convolutional neural networks applied to data organized as OLAP cubes

GNN Graph Classification In Action: Uncovering Patterns in Time Series Data

Stock Selection Using Machine Learning Based on Financial Ratios

Contact Info

Product

Resources

About