• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3218-3241
• /
• 2023

Financial fraud undermines the sustainable development of financial markets. Financial statements can be regarded as the key source of information to obtain the operating conditions of listed companies. Current research focuses more on mining financial digital data instead of looking into text data. However, text data can reveal emotional information, which is an important basis for detecting financial fraud. The audit opinion of the financial statement is especially the fair opinion of a certified public accountant on the quality of enterprise financial reports. Therefore, this research was carried out by using the data features of 4,153 listed companies' financial annual reports and audits of text opinions in the past six years, and the paper puts forward a financial fraud detection model integrating audit opinions. First, the financial data index database and audit opinion text database were built. Second, digitized audit opinions with deep learning Bert model was employed. Finally, both the extracted audit numerical characteristics and the financial numerical indicators were used as the training data of the LightGBM model. What is worth paying attention to is that the imbalanced distribution of sample labels is also one of the focuses of financial fraud research. To solve this problem, data enhancement and Focal Loss feature learning functions were used in data processing and model training respectively. The experimental results show that compared with the conventional financial fraud detection model, the performance of the proposed model is improved greatly, with Area Under the Curve (AUC) and Accuracy reaching 81.42% and 78.15%, respectively.

• Journal of Information Processing Systems
• /
• v.20 no.3
• /
• pp.391-398
• /
• 2024

Given the further promotion of economic globalization, China's financial market has also expanded. However, at present, this market faces substantial risks. The main financial and economic risks in China are in the areas of policy, credit, exchange rates, accounting, and interest rates. The current status of China's financial market is as follows: insufficient attention from upper management; insufficient innovation in the development of the financial economy; and lack of a sound financial and economic risk protection system. To further understand the current situation of China's financial market, we conducted a questionnaire survey on the financial market and reached the following conclusions. A comprehensive enterprise questionnaire from the government's perspective, the enterprise's perspective and the individual's perspective showed that the following problems exist in the financial and economic risk prevention aspects of big data and Internet of Things in China. The political system at the country's grassroots level is not comprehensive enough. The legal regulatory system is not comprehensive enough, leading to serious incidents of loan fraud. The top management of enterprises does not pay enough attention to financial risk prevention. Therefore, we constructed a financial and economic risk prevention model based on big data and Internet of Things that has effective preventive capabilities for both enterprises and individuals. The concept reflected in the model is to obtain data through Internet of Things, use big data for screening, and then pass these data to the big data analysis system at the grassroots level for analysis. The data initially screened as big data are analyzed in depth, and we obtain the original data that can be used to make decisions. Finally, we put forward the corresponding opinions, and their main contents represent the following points: the key is to build a sound national financial and economic risk prevention and assessment system, the guarantee is to strengthen the supervision of national financial risks, and the purpose is to promote the marketization of financial interest rates.

• Journal of Information Technology Services
• /
• v.23 no.1
• /
• pp.97-121
• /
• 2024

As data usage grows in importance, ensuring individual control over personal information becomes critical. The emergence of the 'MyData' concept addresses this, particularly in financial services. Although the institutional and technological framework for financial MyData services is in place, there's a need to establish consumer understanding and perception of its usefulness and safety for successful activation. This study focuses on investigating the impact of trust on the intention to use the new mobile banking service, financial MyData. This study has three objectives. Firstly, to analyze whether trust in financial MyData services and trust in financial MyData service providers affect the intention to use financial MyData services. Secondly, to analyze the process of forming trust in financial MyData services based on the phenomenon of transferring trust in service providers to trust in services. Thirdly, to identify the process by which trust transfer occurs between service providers and financial MyData services. Ultimately, the goal of this study is to promote the intention to use financial MyData services based on the concept of trust and to activate these services. In summary, this study emphasizes the significance of trust in financial MyData services, exploring its impact on user intention and the transfer of trust from providers to services. By promoting consumer trust, the research aims to contribute to the activation of financial MyData services.

• Knowledge Management Research
• /
• v.21 no.2
• /
• pp.177-196
• /
• 2020

Since the adoption of K-IFRS(Korean International Financial Reporting Standards), the amount of financial footnotes has been increased. However, due to the stereotypical phrase and the lack of conciseness, deriving the core information from footnotes is not really easy yet. To propose a solution for this problem, this study tried financial footnote analysis for financial ratio predictions based on text-mining techniques. Using the financial statements data from 2013 to 2018, we tried to predict the earning per share (EPS) of the following quarter. We found that measured prediction errors were significantly reduced when text-mined footnotes data were jointly used. We believe this result came from the fact that discretionary financial figures, which were hardly predicted with quantitative financial data, were more correlated with footnotes texts.

• Journal of the Korean Home Economics Association
• /
• v.39 no.8
• /
• pp.121-136
• /
• 2001

The purpose of this study was to analyze the effects of financial attitudes and financial communication on financial satisfaction. For this study, in 2000, questionnaires developed by the researcher were given to 320 households in Kwangju. resulting in 262 households with usuable data. The data were analyzed by various statistical methods such as frequency, percentile, correlation analysis, t-test, Anova, Multiple Regression analysis. The major findings of this study were as follows; 1) Financial attitudes were significantly different according to age and monthly savings 2) Financial communication was significantly different according to age and financial subjective variables. 3) Financial satisfaction was significantly different according to monthly income, monthly savings, monthly living costs, debt, financial subjective variables and financial communication. The set of socio- economic characteristics variables accounted for 3% of the variance in the financial satisfaction. But the addition of subjective characteristics variables, financial attitude, financial communication resulted in an $R^2$ change of 20, 23, 26%.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.26 no.3
• /
• pp.1-20
• /
• 2001

The amount of financial information in sophisticated large data bases is huge and makes interfirm performance comparisons very difficult or at least very time consuming. The purpose of this paper is to investigate whether neural networks in the form of self-organizing maps (SOM) can be successfully employed to manage the complexity for competitive financial benchmarking. SOM is known to be very effective to visualize results by projecting multi-dimensional financial data into two-dimensional output space. Using the SOM, we overcome the problems of finding an appropriate underlying distribution and the functional form of data when structuring and analyzing a large data base, and show an efficient procedure of competitive financial benchmarking through clustering firms on two-dimensional visual space according to their respective financial competitiveness. For the empirical purpose, we analyze the data base of annual reports of 100 Korean listed companies over the years 1998, 1999, and 2000.

• Communications for Statistical Applications and Methods
• /
• v.15 no.4
• /
• pp.615-631
• /
• 2008

Current credit evaluation models based on only financial data except non-financial data are used continuous data and produce credit scores for the ranking. In this work, some problems of the credit evaluation models based on transformed continuous financial data are discussed and we propose improved credit evaluation models based on categorized financial data. After analyzing and comparing goodness-of-fit tests of two models, the availability of the credit evaluation models for categorized financial data is explained.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.10
• /
• pp.751-759
• /
• 2020

This study examines the impact of mergers on the financial performance of the Jordanian public shareholding companies. The study employs data collected for a sample of 10 Jordanian non-financial public firms that were engaged in legal horizontal merger deals between 2000 and 2013. The data was collected from the published annual financial reports of the merging companies and comparative companies for three years before the merger and three years after the merger. Event study methodology was applied to examine the data. Four measures of financial performance (FP) were used, which are return on assets (ROA), return on equity (ROE), earnings per share (EPS), and net profit margin (NPM). Two methods were used in the analysis - the change model and the intercept model using financial performance raw data and industry-adjusted data. The findings in general showed no significant impact of mergers on the financial performance of merging firms using the change model. However, by using the intercept model, significant impact of mergers on the financial performance was found on the sample of the study. The significant impact was found for mergers on the raw ROE of the merging firms, and on the ROA and NPM of the industry-adjusted firms.

• Journal of Families and Better Life
• /
• v.25 no.3 s.87
• /
• pp.25-44
• /
• 2007

The purpose of this study was to classify the financial strategies and investigate major determinants of the financial performance in elderly households. This study used the data of 4,577households with all ages and 1,255 elderly households were from the Korean Labor and Income Panel Study(2000, 2003). The data were analyzed by various statistical methods such as frequency, mean-test, Duncan's multiple range test, k-mean cluster analysis and regression. The major findings were as follows: First, the classified household financial strategy types were Residual(44.3%), Financial Assets(24.0%), Informal Institutional(19.7%), Diversified Portfolio(7.6%), Real Estate(4.5%). Second, the criteria of classification of the financial strategies were relative, not absolute. Third, elderly households that employed a financial assets had the greatest financial performance (62,320,000 won net gain). Households with all ages that employed a diversified portfolio strategy had the greatest financial performance (98,360,000 won net gain). Forth, the determinants of the financial performance were significantly different according to the types of financial strategy.

• Journal of Information Technology Applications and Management
• /
• v.19 no.1
• /
• pp.13-24
• /
• 2012

Usability and knowledge drawn from utilizing various ways of representing accounting data were examined. Classroom experiments were conducted to compare students' assessment of financial data using table of numbers, 2-dimensional column graphs (2D), 3-dimensional column graphs (3D), and mixed reality visualization of true 3-dimensional graphs (MR). The results showed that in assessing the financial status and performance of a firm, Table of numbers and MR took longer than 2D and 3D graphs. The time spent on true 3D graphs using MR technology was about the same as Table of numbers. When compared the assessment scores of the firm's financial status and performance between participants and experts, the difference was the least when participants used 2D graphs. However, MR was seen as being a new way to provide data of greater complexity and was very useful for financial information.