Credit Rating Change Modeling Using News and Financial Ratios

Lu, Hsin-Min; Tsai, Feng-Tse; Chen, Hsinchun; Hung, Mao‐Wei; Li, Shu-Hsing

doi:10.1145/2361256.2361259

Cited by 19 publications

(6 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cecchini et al (2010) extract concept scores from annual reports in order to develop a financial ontology discriminating between bankrupt/non-bankrupt companies. Lu et al (2012) employ sentiment analysis on the database of news articles. Their results show that topic-specific negative sentiment is more important for future credit rating changes compared with positive sentiment.…”

Section: Forecasting Financial Performance Using Text Information -mentioning

confidence: 99%

Forecasting Corporate Financial Performance Using Sentiment in Annual Reports for Stakeholders’ Decision-Making

Hájek

Olej

Myšková

2014

Technological and Economic Development of Economy

View full text Add to dashboard Cite

This paper is aimed at examining the role of annual reports’ sentiment in forecasting financial performance. The sentiment (tone, opinion) is assessed using several categorization schemes in order to explore various aspects of language used in the annual reports of U.S. companies. Further, we employ machine learning methods and neural networks to predict financial performance expressed in terms of the Z-score bankruptcy model. Eleven categories of sentiment (ranging from negative and positive to active and common) are used as the inputs of the prediction models. Support vector machines provide the highest forecasting accuracy. This evidence suggests that there exist non-linear relationships between the sentiment and financial performance. The results indicate that the sentiment information is an important forecasting determinant of financial performance and, thus, can be used to support decision-making process of corporate stakeholders.

show abstract

Section: Forecasting Financial Performance Using Text Information -mentioning

confidence: 99%

Forecasting Corporate Financial Performance Using Sentiment in Annual Reports for Stakeholders’ Decision-Making

Hájek

Olej

Myšková

2014

Technological and Economic Development of Economy

View full text Add to dashboard Cite

show abstract

“…Regarding the central findings of the identified papers, the importance of the sentiment extracted from financial news for CRA could be shown quite consistently in varying research setups (Janner and Schmidt 2015;Liebmann et al 2016;Lu et al 2012;Norden 2017). The same applies to the volume of news (Tsai et al 2016).…”

Section: Results Analysismentioning

confidence: 78%

34th Bled eConference Digital Support from Crisis to Progressive Change: Conference Proceedings

Pucihar¹,

Borštnar²,

Bons³

et al. 2021

View full text Add to dashboard Cite

The COVID-19 pandemic has presented governments with challenges not only in relation to bio-medical understanding, medical treatment and health facility operations, but also the management of public health, public behaviour and the economy. In the area of public health management, discrete event simulation modelling is capable of providing considerable assistance to decision-makers. In April 2020, on the basis of publicly available information about the virus and its impacts, an analysis was undertaken of the needs of public health policymakers, and a 16-state / 40-flow model was postulated. The model was revisited in December 2020, and experiences around the world applied in order to evaluate the model's apparent usefulness. This resulted in improved appreciation of its applicability and limitations, a revised model, and plans for further evaluation and application. 2 34 TH BLED ECONFERENCE DIGITAL SUPPORT FROM CRISIS TO PROGRESSIVE CHANGE R. Clarke: A Simulation Model for COVID-19 Public Health Management: Design and Preliminary Evaluation 3ill-informed. To constitute information, and to enable the people responsible for public health management to make decisions, data must have context. That context may be provided by each individual policy-maker's own mental model. However, major programmes of this nature involve many stakeholders with diverse perspectives. The context is therefore multi-dimensional, it features competition among values, and the conception of the problem-space needs to be shared rather than personal.The most powerful form of context is provided by models that are shared, that impose some degree of formality on the problem-space, that are sufficiently graphic that all stakeholders can relate to them, and that have an associated terminology that is reasonably common among the stakeholders. Given such a model, it becomes much easier to identify data that would be valuable input to deliberations, to generate and evaluate alternative courses of action, and to assess both the potential and the actual impacts of interventions. 6 34 TH BLED ECONFERENCE DIGITAL SUPPORT FROM CRISIS TO PROGRESSIVE CHANGE ModellingIT was applied to the gathering and publication of data, partly to inform and entertain the public, but more critically to support policy-makers in their efforts to understand the phenomenon. This paper investigates the question as to whether the seeming absence of an 'enterprise model' of the undertaking, and of 'information architecture' and 'data models' to support it, have hampered the potential IT contribution, and hence whether return on investment in IT can be improved by applying insights from modelling theory and practice.A model is a simplified representation of a real-world system, which reflects interdependence among the relevant entities, structures and processes. Real-world socio-economic systems are open, complex and highly inter-connected. Simplification necessarily involves limiting the scope of the model, by placing the focus on one sub-system or two or more closely-related su...

show abstract

“…Therefore, they concluded that CRAs had a significant reaction to the information from the newspapers. Lu et al (2012) revealed that news was helpful to predict future credit ratings, implying that CRAs significantly reacted to the coverages in the newspaper. In this article, we will extend the previous literature to investigate the attitudes of CRAs to the financial news on the internet.…”

Section: Literaturementioning

confidence: 99%

Research on Bond Participants’ Emotion Reactions Toward the Internet News in China’s Bond Market

Zhang

Wang

2022

Front. Psychol.

View full text Add to dashboard Cite

The literature has widely studied the market response to the financial news or events but mainly focused on the stock market. This article associates the concept of internet news with the bond market response and attempts to examine how credit rating agencies (CRAs) and bond investors, two important bond participants, react to financial news on the internet with a range of multiply regressions. Our empirical study leads to several findings. First, CRAs tend to ignore the warnings of financial news on the internet, whereas bond investors strongly react to such news. Second, there is an asymmetry in bond investors’ reactions to good news compared to bad news, with investors being more sensitive to bad news. Third, there is heterogeneity in the psychological reaction where bond investors do not react to the news about central state-owned enterprises (SOEs) but to the news about other enterprises. Finally, there is an asymmetric response driven by news timeliness that bond investors are more sensitive to the latest news articles than old ones. Overall, our study confirms the existence of psychological reactions to the financial news on the internet in China’s bond market, which has significance for keeping bond market participants from overreacting or underreacting to market news.

show abstract

Credit Rating Change Modeling Using News and Financial Ratios

Cited by 19 publications

References 53 publications

Forecasting Corporate Financial Performance Using Sentiment in Annual Reports for Stakeholders’ Decision-Making

Forecasting Corporate Financial Performance Using Sentiment in Annual Reports for Stakeholders’ Decision-Making

34th Bled eConference Digital Support from Crisis to Progressive Change: Conference Proceedings

Research on Bond Participants’ Emotion Reactions Toward the Internet News in China’s Bond Market

Contact Info

Product

Resources

About