|
Journal of Asian Business and Economic Studies |
Vol. 28(4)
, December 2021, Page 303-320
|
|
The implication of machine learning for financial solvency prediction: an empirical analysis on public listed companies of Bangladesh |
|
Mohammad Abdullah |
DOI: 10.1108/JABES-11-2020-0128
Abstract
Purpose
Financial health of a corporation is a great concern for every investor level and decision-makers. For many years, financial solvency prediction is a significant issue throughout academia, precisely in finance. This requirement leads this study to check whether machine learning can be implemented in financial solvency prediction.
Design/methodology/approach
This study analyzed 244 Dhaka stock exchange public-listed companies over the 2015–2019 period, and two subsets of data are also developed as training and testing datasets. For machine learning model building, samples are classified as secure, healthy and insolvent by the Altman Z-score. R statistical software is used to make predictive models of five classifiers and all model performances are measured with different performance metrics such as logarithmic loss (logLoss), area under the curve (AUC), precision recall AUC (prAUC), accuracy, kappa, sensitivity and specificity.
Findings
This study found that the artificial neural network classifier has 88% accuracy and sensitivity rate; also, AUC for this model is 96%. However, the ensemble classifier outperforms all other models by considering logLoss and other metrics.
Research limitations/implications
The major result of this study can be implicated to the financial institution for credit scoring, credit rating and loan classification, etc. And other companies can implement machine learning models to their enterprise resource planning software to trace their financial solvency.
Practical implications
Finally, a predictive application is developed through training a model with 1,200 observations and making it available for all rational and novice investors (Abdullah, 2020).
Originality/value
This study found that, with the best of author expertise, the author did not find any studies regarding machine learning research of financial solvency that examines a comparable number of a dataset, with all these models in Bangladesh.
Keywords
Financial distress, Machine learning, Artificial neural network, Ensemble classifier, Bankruptcy prediction
|
|
|
Do average higher moments predict aggregate returns in emerging stock markets?
2022, Journal of Asian Business and Economic Studies
More
Abstract
Purpose
It has been demonstrated in the US market that expected market excess returns can be predicted using the average higher-order moments of all firms. This study aims to empirically test this theory in emerging markets.
Design/methodology/approach
Two measures of average higher moments have been used (equal-weighted and value-weighted) along with the market moments to predict subsequent aggregate excess returns using the linear as well as the quantile regression model.
Findings
The authors report that both equal-weighted skewness and kurtosis significantly predict subsequent market returns in two countries, while value-weighted average skewness and kurtosis are significant in predicting returns in four out of nine sample markets. The results for quantile regression show that the relationship between the risk variable and aggregate returns varies along the spectrum of conditional quantiles.
Originality/value
This is the first study that investigates the impact of third and fourth higher-order average realized moments on the predictability of subsequent aggregate excess returns in the MSCI Asian emerging stock markets. This study is also the first to analyze the sensitivity of future market returns over various quantiles.
Improving the quality of the financial accounting information through strengthening of the financial autonomy at public organizations
2022, Journal of Asian Business and Economic Studies
More
Abstract
Purpose
The purpose of this study is to examine the financial autonomy that affects the financial accounting information quality of public organizations. This study also tests the impact of the financial autonomy on support from leadership. How this impact has affected elements of accounting information systems such as hardware, software, communications technology and chief accountant to support providing the quality of the financial accounting information.
Design/methodology/approach
The research model is in the SEM form and measurement models are reflective scales so this study applies the PLS-SEM analysis technique on the Smart PLS 3.2.7 software to test the research hypotheses. Analytical data is collected through survey questionnaires with observed variables measured using the typical 7-point Likert scales. The result obtained after cleaning the data includes 164 Vietnamese public organizations with the different levels of the financial autonomy.
Findings
This research has three primary findings: firstly, FA has a positive direct effect on FAIQ and SL. Secondly, SL influences FAIQ through four mediate variables including AM, HW, SW and CN. Finally, SL also acts as a mediate variable in the relationship of FA and FAIQ.
Originality/value
This is one of the first empirical studies to examine the role of financial autonomy in leadership support to improve the quality of the accounting information in the public sector in the context of the Vietnamese government is promoting the financial autonomy of public organizations.
Characteristics of consulting firms associated with the diffusion of big data analytics
2021, Journal of Asian Business and Economic Studies
More
Abstract
Purpose
This study investigates the characteristics of business and management consulting firms (firm size, international affiliation and scope of operation) affecting the adoption rate (i.e. recency of adopting big data analytics (BDA) as a new idea) and usage level of BDA. Ten critical areas of BDA application to business and management consulting were investigated, (1) Human Resource Management; (2) Risk Management; (3) Financial Advisory Services; (4) Innovation and Strategy; (5) Brand Building and Product Positioning; (6) Market Research/Diagnostic Studies; (7) Scenario-Based Planning/Business Simulation; (8) Information Technology; (9) Internal Control/Internal Audit; and (10) Taxation and Tax Management.
Design/methodology/approach
Survey data was obtained through a structured questionnaire from one hundred and eighteen (118) consultants in Nigeria from diverse consulting firm settings in terms of size, international affiliation and scope of operation (Big 4/non-Big 4 firms). Data was analyzed using descriptive statistics, cluster analysis, multivariate analysis of variance (MANOVA), multivariate discriminant analysis and multivariable logistic regression.
Findings
Whereas organizational characteristics such as firm size, international affiliation and scope of operation significantly determine the adoption rate of BDA, two attributes (international affiliation and scope of operation) significantly explain BDA usage level. Internationally affiliated consulting firms are more likely to record higher usage level of BDA than local firms. Also, the usage level of BDA by the Big 4 accounting/consulting firms is expected to be higher in comparison to non-Big 4 firms.
Practical implications
Contrary to common knowledge that firm size is positively associated with the adoption of an innovation, the study found no evidence to support this claim in respect of the diffusion of BDA. Overall, it appears that the scope of operation is the strongest organizational factor affecting the diffusion of BDA among consulting firms.
Originality/value
The study contributes to knowledge by exposing the factors promoting the uptake of BDA in a developing country. The originality of the current study stems from the consideration that it is the first, to the researchers' knowledge, to investigate the application of BDA by consulting firms in the Nigerian context. The study adds to literature on management accounting in the digital economy.
Dividend policy and earnings quality in Vietnam
2020, Journal of Asian Business and Economic Studies
More
Abstract
Purpose
The purpose of this paper is to examine the relationship between dividend policy and earnings quality of Vietnamese listed firms.
Design/methodology/approach
The sample includes firms listed on Vietnam stock exchange during the period between 2010 and 2016. Two measures of earnings quality are the annual firm-specific absolute value of residuals from Dechow and Dichev’s (2002) model and from Dechow and Dichev (2002) as modified by McNichols’s (2002) model. The firms’ dividend policy is captured by dividend paying status. This is a dummy variable that takes the value of 1 if the firm pays dividends and 0 otherwise. In addition, dividend yield and dividend payout ratio, which are continuous variables, are also used in this paper as alternative proxies for dividend policy.
Findings
Using panel data analysis, this paper documents that dividend payers have higher earnings quality than dividend non-payers. Dividends are an indicator of earnings quality. These findings are consistent with prior studies. After controlling for variables that may be related to earnings quality as well as for the year and industry fixed effects, this relation remains unchanged. In addition, this result is also robust after controlling for firm fixed effects.
Originality/value
This paper offers the empirical evidence on the relation between dividend policy and earnings quality in Vietnam, which is a frontier market.
Asymmetric targeting of corporate cash holdings and financial constraints in Pakistani firms
2020, Journal of Asian Business and Economic Studies
More
Abstract
Purpose – The purpose of this paper is to investigate the asymmetric adjustment of cash holdings in Pakistani firms for above and below target firms.
Design/methodology/approach – The study employs generalized method of moments (GMM) to investigate the adjustment of cash holdings.
Findings – The study found that the firms which hold cash above the optimal level of cash holdings have higher speed of adjustment than the firms which hold cash below the optimal level. Financially constrained (FC) firms also adjust their cash holdings faster than financially unconstrained (FUC) firms but high speed of downward adjustment does not remain persistent after financial constraints are controlled. Findings of this study reveal this asymmetric adjustment in above and below target firms and extend these results in FC and FUC Pakistani listed firms, respectively.
Research limitations/implications – The conclusion of this study has been derived under certain limitations. There is a vast space to extend this study in different dimensions. Firms operating in capital-intensive industries may provide different results for financial constraints because their policy designing would be quite different from other firms.
Originality/value – This study contributes to cash holdings research in Pakistan by exploring the adjustment behavior of cash holdings across Pakistani non-financial firms using econometric modeling. Downward adjustment rate is supposed to be higher than upward adjustment rate and this rate is tested using dynamic panel data model. Similarly, it is inferred that this relationship holds for above target firms even after including the financial constraints in the presented model.
|