Feature Selection Optimization Model for Business Risk Assessment Model

2021 ◽  
pp. 51-64
Author(s):  
Noura Metawa ◽  
◽  
◽  
Mohamed Elhoseny

Financial risk assessment becomes a hot research topic among financial firms or companies to assess the financial status and thereby avoid future crises. Earlier studies have focused on statistical models for the assessment of financial risks and the recently developed machine learning (ML) models find useful to improve the assessment performance. In this aspect, this study introduces a novel Butterfly Optimization based Feature Selection with Classification Model for Financial Risk Assessment (BOFS-CFRA) technique. The proposed BOFS-CFRA technique involves pre-processing at the primary stage to get rid of unwanted data. In addition, K-means clustering approach is developed to group the financial data into clusters. Then, the BOFS technique is applied to choose the subset of features from the clustered data. Finally, the classification of financial risks takes place by the use of functional link neural network (FLNN). In order to ensure the enhanced performance of the BOFS-CFRA technique, a series of simulations were carried out and the results are inspected under various measures. The simulation outcome portrayed the supremacy of the BOFS-CFRA technique over the other financial risk assessment models in terms of several performance measures.

2020 ◽  
Vol 9 (28) ◽  
pp. 451-464
Author(s):  
Viktoriya Manuylenko ◽  
Denis Ryzin ◽  
Natalia Gryzunova ◽  
Olga Bigday ◽  
Olga Mandrytsa

The study substantiates the need to develop and test a model for assessment of strategic financial risk level in corporations. It implies modeling for two indicators: relative (financial leverage) and absolute (external capital of indicators). The model should also take into account influence of emergent environment factors and most stakeholder groups’ interests when building scenarios for their behaviors in the financial markets –Implementation of the model allows establishing financial risk target values considering deviation calculations between the indicators’ modeled and actual values simultaneously determining both tactical and strategic guidelines for Financial Risk Management Policy in corporations, which should involve stakeholders into financial risk-taking process. The model implementation also should be the basis for development and improvement of risk-based forecasting tools, business planning and stress testing. The toolkit for assessing level of current and strategic financial risks in corporations based on simulation modeling was developed and implemented with attraction of general scientific and special methods. Direct results of the study are as follows: in theoretical block of the research – essentially, main attributes of financial risks classification for corporations are identified; they are recognized by time as retrospective, current and strategic financial risks, and correct classification of the latter allows their identification, evaluation and regulation; in practical block of the research – evaluation of financial risk in corporations reveals that the risk apart from other internal factors is highly affected by the level of financial leverage, where its high value increases financial risk; still, corporations do not take into account the influence of environmental factors on its level; the role of tax risk as a part of financial risk is not significant, still it is unfortunate that the Russian legislation system allows double taxation on income tax in the form of dividends, and dividend policy of Russian corporations is unstable; in methodological block of the research –financial risk assessment model for corporations was developed and tested on a platform of a special new software product that determines the target level of financial risk; the model differs from standard approaches to financial risk assessment as it carries strategic forecasting nature and takes into account the impact of emergent environment factors; thus it promotes new areas in strategic financial risk management.


2020 ◽  
Vol 22 (1) ◽  
pp. 6-12
Author(s):  
Nelia Volkova ◽  
◽  
Alina Mukhina ◽  

Abstract. Introduction. The issue of financial risk management of commercial banks is quite relevant today, because the activity of banks is the most risky of all. The presence of risks in banking can lead to unexpected losses, namely the loss of own resources. That’s why for the stable operation of the bank without loss the priority is to assess the financial risks, which is the basis for their further neutralization. Purpose. The purpose of the article is to develop conceptual provisions for assessment financial risks and justifying the need to neutralize them. Results. The article analyzes the impact of risks on the financial stability of a banking institution. The main methods of bank risk assessment are considered. All these include the statistical method, the analytical method, the expert method, the analogue method and the combined method. The necessity of neutralization of financial risks in order to avoid negative consequences is substantiated. Also the methods of bank risks neutralization are considered. It should be noted that these methods of neutralization can not only be used, but also supplement the list with new methods must be done, which in the future will protect the bank from the influence of undesirable factors. A conceptual approach to the assessment and neutralization of financial risks is proposed. This conceptual approach aims to ensure effective assessment of the level of risk with their subsequent neutralization Conclusions. Use of a conceptual approach will allow an effective risk assessment and decision-making to avoid or accept risk. Thanks to using this approach, the banking institution will be able to react swiftly to the presence of financial risks and to prevent the occurrence of negative consequences, which may lead to a violation of the financial stability of the bank.


2019 ◽  
Vol 20 (3) ◽  
pp. 226-248 ◽  
Author(s):  
Thomas Michael Brunner-Kirchmair ◽  
Melanie Wiener

Purpose Inspired by new findings on and perceptions of risk governance, such as the necessity of taking a broader perspective in coping with risks in companies and working together in interactive groups with various stakeholders to deal with complex risks in the modern world, the purpose of this paper is looking for new ways to deal with financial risks. Current methods dealing with those risks are confronted with the problems of being primarily based on past data and experience, neglecting the need for objectivity, focusing on the short-term future and disregarding the interconnectedness of different financial risk categories. Design/methodology/approach A literature review of risk governance, financial risk management and open foresight was executed to conceptualize solutions to the mentioned-above problems. Findings Collaborative financial risk assessment (CFRA) is a promising approach in financial risk governance with respect to overcoming said problems. It is a method of risk identification and assessment, which combines aspects of “open foresight” and the financial risk management and governance literature. CFRA is characterized as bringing together members of different companies in trying to detect weak signals and trends to gain knowledge about the future, which helps companies to reduce financial risks and increase the chance of gaining economic value. By overcoming organizational boundaries, individual companies may gain the knowledge they would probably not have without CFRA and achieve a competitive advantage. Research limitations/implications A conceptual paper like the one at hand wants empirical proof. Therefore, the authors developed a research agenda in the form of five propositions for further research. Originality/value This paper discusses the existing problems of financial risk identification and assessment methods. It contributes to the existing literature by proposing CFRA as a solution to those problems and adding a new perspective to financial risk governance.


Diversity ◽  
2019 ◽  
Vol 11 (9) ◽  
pp. 164 ◽  
Author(s):  
Oldřich Kopecký ◽  
Anna Bílková ◽  
Veronika Hamatová ◽  
Dominika Kňazovická ◽  
Lucie Konrádová ◽  
...  

Because biological invasions can cause many negative impacts, accurate predictions are necessary for implementing effective restrictions aimed at specific high-risk taxa. The pet trade in recent years became the most important pathway for the introduction of non-indigenous species of reptiles worldwide. Therefore, we decided to determine the most common species of lizards, snakes, and crocodiles traded as pets on the basis of market surveys in the Czech Republic, which is an export hub for ornamental animals in the European Union (EU). Subsequently, the establishment and invasion potential for the entire EU was determined for 308 species using proven risk assessment models (RAM, AS-ISK). Species with high establishment potential (determined by RAM) and at the same time with high potential to significantly harm native ecosystems (determined by AS-ISK) included the snakes Thamnophis sirtalis (Colubridae), Morelia spilota (Pythonidae) and also the lizards Tiliqua scincoides (Scincidae) and Intellagama lesueurii (Agamidae).


2020 ◽  
Vol 11 (3) ◽  
pp. 73
Author(s):  
Mazni Asrida Abdullah ◽  
Azlina Ahmad ◽  
Nor Azam Mat Nayan ◽  
Zubir Azhar ◽  
Abd-Razak Ahmad

Internal ratings have been used by banks to evaluate the creditworthiness of their borrowers with diverse practices. This research aims to analyse the practice of assessing (or predicting) the credit performance of microfinancing loans of a Malaysian bank and to suggest how the existing performance of credit assessment model can be improved. Logistic regression was used to investigate the predictive ability of information on business operators’ management and accounting skills as factors to predict default risk of borrowers. The combination of these information formed the three (3) models that were used in the analysis. The accuracy rate of each model was then measured. A sample of respondents was selected among microfinance borrowers in a national savings bank’s branch in Malaysia. A total of 106 questionnaires were used for data analysis. The findings suggest that good credit rating, business experience, business financial and forecasting capability are factors associated with whether SMEs will default or not in their payments. The combination of credit score used currently by the bank and the new information produced by this research increases the bank’s ability to predict default.


PLoS ONE ◽  
2018 ◽  
Vol 13 (12) ◽  
pp. e0208166 ◽  
Author(s):  
Dan-Ping Li ◽  
Si-Jie Cheng ◽  
Peng-Fei Cheng ◽  
Jian-Qiang Wang ◽  
Hong-Yu Zhang

Author(s):  
Anastasia Filiana Ismawati

Risk management by using risk mapping can help X Hospital located in Yogyakarta in financial management towards operating as an objective company. Enterprise Risk Management (ERM) helps organizations manage all the risks precisely and in a more integrated way. This research focuses on the risk assessment in X hospital that has not applied ERM, to analyse its financial risks. From this test, X Hospital is expected to manage its risks by using the ERM methods more, in order than the sustainability of the business can be maintained over a longer period, and thus, being able to compete with the competitors. Based on the results of risk the assessment, out of the 15 risks identified. There are top three risks that cannot be acceptable. They are: financial management report risk, contribution risk and multiple jobs risk of X Hospital. The three risks need to get response and allocations of good funds and attention from the management.


2019 ◽  
Vol 48 (4) ◽  
pp. 030006051989317
Author(s):  
Xindan Wang ◽  
Jing Huang ◽  
Zhao Bingbing ◽  
Shape Li ◽  
Li Li

Objective This study aimed to investigate a suitable risk assessment model to predict deep vein thrombosis (DVT) in patients with gynecological cancer. Methods Data from 212 patients with gynecological cancer in the Affiliated Tumor Hospital of Guangxi Medical University were retrospectively analyzed. Patients were risk-stratified with three different risk assessment models individually, including the Caprini model, Wells DVT model, and Khorana model. Results The difference in risk level evaluated by the Caprini model was not different between the DVT and control groups. However, the DVT group had a significantly higher risk level than the control group with the Wells DVT or Khorana model. The Wells DVT model was more effective for stratifying patients in the DVT group into the higher risk level and for stratifying those in the control group into the lower risk level. Receiver operating curve analysis showed that the area under the curve of the Wells DVT, Khorana, and Caprini models was 0.995 ± 0.002, 0.642 ± 0.038, and 0.567 ± 0.039, respectively. Conclusion The Wells DVT model is the most suitable risk assessment model for predicting DVT. Clinicians could also combine the Caprini and Wells DVT models to effectively identify high-risk patients and eliminate patients without DVT.


2020 ◽  
Vol 86 (9) ◽  
pp. 1098-1105
Author(s):  
Eli Mlaver ◽  
Grant C. Lynde ◽  
Claire Gallion ◽  
John F. Sweeney ◽  
Jyotirmay Sharma

Introduction Standardization of preoperative venous thromboembolism (VTE) risk assessment remains challenging due to variation in risk assessment models (RAMs) and the cumbersome workflow addition that most RAMs represent. We aimed to develop a parsimonious RAM that is automatable and actionable within the preoperative workflow. Methods We performed a case-controlled review of all 18 VTE cases reported over a 12-month period and 171 matched controls included in an institutional National Surgical Quality Improvement Project (NSQIP) data set. We examined the predictive value of the Caprini, Padua, and NSQIP RAMs. We identified the 5 most impactful risk factors in VTE development by contribution to the known RAMs. We compared the predictive ability of cancer, age, body mass index, black race, and American Society of Anesthesiologists Physical Status (ASA-PS) score, to the Caprini, Padua, and NSQIP RAMs for VTE outcomes. Finally, we evaluated concordance between each of the models. Results The Caprini Score was found to be 88.9% sensitive and 32.7% specific using a threshold of 5. The Padua score was found to be 61.1% sensitive and 47.4% specific using a threshold of 4. The novel 5-factor RAM was found to be 94.4% sensitive and 38.0% specific using a threshold of 4. The Caprini and Padua models were discordant in 26% of patients. Discussion Cumbersome manual data entry contributes to the ongoing challenge of standardized VTE risk assessment and prophylaxis. Universally documented information and patient demographics can be utilized to create clinical decision support tools that can improve the efficiency of perioperative workflow and improve the quality of care.


Sign in / Sign up

Export Citation Format

Share Document