Search results

Accounting information systems are mainly rule-based, and data are usually available and well-structured. However, many accounting systems are yet to catch up with current technological developments. Thus, artificial intelligence (AI) in financial accounting is often applied only in pilot projects. Using AI-based forecasts in accounting enables proactive management and detailed analysis. However, thus far, there is little knowledge about which prediction models have already been evaluated for accounting problems. Given this lack of research, our study aims to summarize existing findings on how AI is used for forecasting purposes in financial accounting. Therefore, the authors aim to provide a comprehensive overview and agenda for future researchers to gain more generalizable knowledge.

The authors identify existing research on AI-based forecasting in financial accounting by conducting a systematic literature review. For this purpose, the authors used Scopus and Web of Science as scientific databases. The data collection resulted in a final sample size of 47 studies. These studies were analyzed regarding their forecasting purpose, sample size, period and applied machine learning algorithms.

The authors identified three application areas and presented details regarding the accuracy and AI methods used. Our findings show that sociotechnical and generalizable knowledge is still missing. Therefore, the authors also develop an open research agenda that future researchers can address to enable the more frequent and efficient use of AI-based forecasts in financial accounting.

Owing to the rapid development of AI algorithms, our results can only provide an overview of the current state of research. Therefore, it is likely that new AI algorithms will be applied, which have not yet been covered in existing research. However, interested researchers can use our findings and future research agenda to develop this field further.

Given the high relevance of AI in financial accounting, our results have several implications and potential benefits for practitioners. First, the authors provide an overview of AI algorithms used in different accounting use cases. Based on this overview, companies can evaluate the AI algorithms that are most suitable for their practical needs. Second, practitioners can use our results as a benchmark of what prediction accuracy is achievable and should strive for. Finally, our study identified several blind spots in the research, such as ensuring employee acceptance of machine learning algorithms in companies. However, companies should consider this to implement AI in financial accounting successfully.

To the best of our knowledge, no study has yet been conducted that provided a comprehensive overview of AI-based forecasting in financial accounting. Given the high potential of AI in accounting, the authors aimed to bridge this research gap. Moreover, our cross-application view provides general insights into the superiority of specific algorithms.

This paper investigates the predictive impact of Financial Stress on hedging between the oil market and the GCC stock and bond markets from January 1, 2007, to December 31, 2020. The authors also compare the hedging performance of in-sample and out-of-sample analyses.

For the modeling purpose, the authors combine the GARCH-BEKK model with the machine learning approach to predict the transmission of shocks between the financial markets and the oil market. The authors also examine the hedging performance in order to obtain well-diversified portfolios under both Financial Stress cases, using a One-Dimensional Convolutional Neural Network (1D-CNN) model.

According to the results, the in-sample analysis shows that investors can use oil to hedge stock markets under positive Financial Stress. In addition, the authors prove that oil hedging is ineffective in reducing market risks for bond markets. The out-of-sample results demonstrate the ability of hedging effectiveness to minimize portfolio risk during the recent pandemic in both Financial Stress cases. Interestingly, hedgers will have a more efficient hedging performance in the stock and oil market in the case of positive (negative) Financial Stress. The findings seem to be confirmed by the Diebold-Mariano test, suggesting that including the negative (positive) Financial Stress in the hedging strategy displays better out-of-sample performance than the in-sample model.

This study improves the understanding of the whole sample and positive (negative) Financial Stress estimates and forecasts of hedge effectiveness for both the out-of-sample and in-sample estimates. A portfolio strategy based on transmission shock prediction provides diversification benefits.

Using various proxies for the firms' return on equity (ROE) and retention ratios (b) the authors calculate 36 sustainable growth rates, on a rolling basis, for a comprehensive set of firms over a 52-year period. The authors then assess the ability of these different sustainable growth rates to predict the actual, out-of-sample, five-year growth rates of the firms' earnings.

The authors compare the forecast to determine which method of estimating ROE and b produce the lowest mean-squared-errors and then determine the estimation method that works best for firms with different characteristics and for firms in different industries.

Overall, using the median ROE of all firms in the market and the 5-year average of the specific firm's retention ratio produces the lowest, statistically significant, forecast errors. Variations are documented based on firm characteristics, including dividend payout, level of ROE and industry.

The findings can guide practitioners in using the best earnings forecasting method.

Financial textbooks seem universally to suggest that one method of estimating the growth rate of a firm's earnings is to calculate the “sustainable growth rate” by multiplying the firm's ROE by the firm's b. At the same time, multiple methods of proxying for both ROE and b have been suggested; therefore, it is an interesting and useful empirical question, which, heretofore, has not been addressed in the literature, as to which estimation of the sustainable growth rate best approximates the actual future growth of the firm's earnings. The findings can guide practitioners in using the best earnings forecasting method.

This study seeks to build a financial uncertainty index for Saudi Arabia. This index serves as a leading indicator of Saudi economic activity and helps to describe economic fluctuations and forecast economic trends.

This study adopts an extension of the Jurado et al. (2015) procedure by combining financial uncertainty factors with their net spillover effects on GDP and inflation to construct an aggregate financial uncertainty index. The authors consider 13 monthly financial variables for Saudi Arabia from January 2010 to June 2021.

The empirical results show that the constructed financial uncertainty estimates are good leading indicators of economic activity. The robustness analysis suggests that the authors’ proposed financial uncertainty estimators outperform the alternative estimates used by other existing approaches to estimate the financial conditions index.

To the best of the authors’ knowledge, this is the first attempt at constructing a financial uncertainty index for Saudi Arabia. This study extends the empirical literature, from which the authors propose a novel conceptual framework for building a financial uncertainty index by combining the approach of Jurado et al. (2015) and the time-varying connectedness network approach proposed by Antonakakis et al. (2020)

This article examines the link between the structure of the board of directors and target price accuracy using a sample of 51 listed firms on the Tunisian Stock Exchange over the period of 2011–2017.

In this study, the authors used the generalised method of moments (GMM) model to control the endogeneity problem.

As a result, that model can serve as a signal in the forecasting process. The authors' results suggest that target price accuracy is negatively related to board independence, and dual Chief Executive officer (CEO). In addition, CEO compensation tends to exert a negative impact on target price error.

The authors' findings are valuable for common investors because the findings can be useful in enhancing their capital allocation decisions by assigning higher weights to forecasts issued by firms with strong corporate governance systems. The authors' study also has practical implications for managers and policymakers. Specifically, the evidence provided herein suggests that firms with strong corporate governance mechanisms enhance the accuracy of market expectations, alleviate information asymmetry, and limit market surprises, especially in a context characterised by weak investor protection. The authors' results highlight the advantages of strong corporate governance in improving a firm's information environment and, therefore, are useful for the cost–benefit analysis of improving internal governance mechanisms. Additionally, the authors' results may prove useful to investors who can rely on the information provided by analysts for well-governed companies.

The authors' study contributes to the literature in both corporate governance and analysts' forecasts fields. The study provides additional evidence of the benefit of board quality attributes on target price accuracy in an emerging market characterised by high information asymmetry and weak investor protection. The authors' findings exhibit the effectiveness of board attributes in producing better financial information quality in Tunisia. This is useful for investors who may improve their capital allocation decisions by assigning greater weights to target price forecasts of companies with good governance quality, suggesting that good corporate governance is a credible signal of better financial information quality. These results have important implications for capital market regulators and corporate management in encouraging the implementation of good governance practices.

The authors attempted to assess whether corporate governance of listed firms are priced in the Tunisian context characterised by weak governance control and to highlight which mechanism is highly considered by independent financial analysts to build their forecasts.

The main purpose of this paper is to predicate financial distress using the worst-practice-frontier data envelopment analysis (WPF-DEA) model and artificial neural network.

In this study, a neural network technique was used to forecast inputs and outputs in the future time-period. Using a WPF-DEA model, financially distressed companies were identified based on the worst performance, and an improvement solution was provided for those decision-making units.

This study’s findings show that dynamic WPF-DEA has high predictability in corporate financial distress, and it can be used with high confidence. Based on the future time-period results, JOUSH & OXYGEN was predicted to be a financially distressed company in the two future time-periods.

In recent decades, globalization, technological changes and a competitive space have increased uncertainty in the economic environment. In such circumstances, economic growth certainly depends on correct decision-making and optimal allocation of resources. It can be done by introducing appropriate tools and models for assessing corporate financial conditions, including financial distress and bankruptcy.

Digital currency investment has emerged as a result of global transformation toward technology-driven human lives. In Asia, Malaysia as an Islamic country is one of the early adopters with a high level of awareness on cryptocurrency. This paper aims to investigate the factors affecting the investment decision in cryptocurrency among potential investors in Malaysia.

Data was collected from 200 individuals aged 18 years and over. The hypotheses were tested using the partial least squares – structural equation modeling technique.

Results showed that attitude toward risk and perceived behavioral control have a significant positive effect on the investor’s investment decision in cryptocurrency. Interestingly, machine learning forecasting enhances the relationship between perceived benefits and the investment decision in cryptocurrency.

Results benefit investors and practitioners on the significant determinants of investment decision in cryptocurrency in emerging market.

Despite having high volatility and complexity in price determination, and being decentralized, cryptocurrency has managed to attract many investors due to reasons less explored. The outcome of this study extends the theory of planned behavior and confirms the role of machine learning forecasting as a moderator in the context of cryptocurrency investment.

The present study is intended to develop an effective approach to the real-time modeling of general dynamic nonlinear systems based on the multidimensional Taylor network (MTN).

The authors present a detailed explanation for modeling the general discrete nonlinear dynamic system by the MTN. The weight coefficients of the network can be obtained by sampling data learning. Specifically, the least square (LS) method is adopted herein due to its desirable real-time performance and robustness.

Compared with the existing mainstream nonlinear time series analysis methods, the least square method-based multidimensional Taylor network (LSMTN) features its more desirable prediction accuracy and real-time performance. Model metric results confirm the satisfaction of modeling and identification for the generalized nonlinear system. In addition, the MTN is of simpler structure and lower computational complexity than neural networks.

Once models of general nonlinear dynamical systems are formulated based on MTNs and their weight coefficients are identified using the data from the systems of ecosystems, society, organizations, businesses or human behavior, the forecasting, optimizing and controlling of the systems can be further studied by means of the MTN analytical models.

MTNs can be used as controllers, identifiers, filters, predictors, compensators and equation solvers (solving nonlinear differential equations or approximating nonlinear functions) of the systems of ecosystems, society, organizations, businesses or human behavior.

The operating efficiency and benefits of social systems can be prominently enhanced, and their operating costs can be significantly reduced.

Nonlinear systems are typically impacted by a variety of factors, which makes it a challenge to build correct mathematical models for various tasks. As a result, existing modeling approaches necessitate a large number of limitations as preconditions, severely limiting their applicability. The proposed MTN methodology is believed to contribute much to the data-based modeling and identification of the general nonlinear dynamical system with no need for its prior knowledge.

This study updates the literature review of Jones (1987) published in this journal. The study pays particular attention to two important themes that have shaped the field over the past 35 years: (1) the development of a range of innovative new statistical learning methods, particularly advanced machine learning methods such as stochastic gradient boosting, adaptive boosting, random forests and deep learning, and (2) the emergence of a wide variety of bankruptcy predictor variables extending beyond traditional financial ratios, including market-based variables, earnings management proxies, auditor going concern opinions (GCOs) and corporate governance attributes. Several directions for future research are discussed.

This study provides a systematic review of the corporate failure literature over the past 35 years with a particular focus on the emergence of new statistical learning methodologies and predictor variables. This synthesis of the literature evaluates the strength and limitations of different modelling approaches under different circumstances and provides an overall evaluation the relative contribution of alternative predictor variables. The study aims to provide a transparent, reproducible and interpretable review of the literature. The literature review also takes a theme-centric rather than author-centric approach and focuses on structured themes that have dominated the literature since 1987.

There are several major findings of this study. First, advanced machine learning methods appear to have the most promise for future firm failure research. Not only do these methods predict significantly better than conventional models, but they also possess many appealing statistical properties. Second, there are now a much wider range of variables being used to model and predict firm failure. However, the literature needs to be interpreted with some caution given the many mixed findings. Finally, there are still a number of unresolved methodological issues arising from the Jones (1987) study that still requiring research attention.

The study explains the connections and derivations between a wide range of firm failure models, from simpler linear models to advanced machine learning methods such as gradient boosting, random forests, adaptive boosting and deep learning. The paper highlights the most promising models for future research, particularly in terms of their predictive power, underlying statistical properties and issues of practical implementation. The study also draws together an extensive literature on alternative predictor variables and provides insights into the role and behaviour of alternative predictor variables in firm failure research.

The idea of this study is to provide a solid Financial Condition Index (FCI) that allows the monetary transmission policy to be monitored in a country which in recent decades has suffered from major financial and monetary crises.

The authors construct three FCIs for Mexico to analyse the role of financial asset prices in formulating monetary policy under an inflation-targeting regime. Using monthly data from 1995 to 2017, the authors estimate FCIs with two different methodologies and build the index by taking into account the mechanism of transmission of monetary policy and incorporating the most relevant financial variables.

This study’s results show that, likewise for developing countries as Mexico, an FCI could be a useful tool for managing monetary policy in reducing macroeconomic fluctuations.

Apart from building a predictor of possible financial stress, the authors construct an FCI for a central bank that pursues inflation targeting and to analyse the role of financial asset prices in formulating monetary policy.

1. We construct three FCIs for Mexico to analyse the role of financial asset prices in formulating monetary policy under an inflation-targeting regime.

2. The FCIs are based on (1) a vector autoregression model (VAR); (2) an autoregressive distributed lag model (ARDL) and (3) a factor-augmented vector autoregression model (FAVAR).

3. FCI could become a new target for monetary policy within a hybrid inflation-targeting framework.

4. FCI could be a good tool for managing monetary policy in developing countries with a low-inflation environment.

We construct three FCIs for Mexico to analyse the role of financial asset prices in formulating monetary policy under an inflation-targeting regime.

The FCIs are based on (1) a vector autoregression model (VAR); (2) an autoregressive distributed lag model (ARDL) and (3) a factor-augmented vector autoregression model (FAVAR).

FCI could become a new target for monetary policy within a hybrid inflation-targeting framework.

FCI could be a good tool for managing monetary policy in developing countries with a low-inflation environment.