Artificial Neural Networks Applied to Ratio Analysis in the Analytical Review Process

Experts claim that artificial neural network (ANN) technology can outperform standard statistical methods when applied to examine actual financial data. Researchers have used ANNs to analyze bankruptcy prediction, bond rating and the going-concern problem. Financial firms have employed ANNs commercially to predict commercial bank failures, detect credit card fraud and verify signatures. For accounting and auditing problems, however, application of ANN technology has been limited. Preliminary experiments tested whether an ANN offered improved performance in recognizing material misstatements during the analytical review process of auditing. Four years of audited financial data from a medium-sized distributor were input as data streams to calibrate the ANN across fifteen financial accounts. Researchers compared a presumed lack of actual errors and certain seeded material errors with signals from the ANN analytical review process to evaluate performance. Results were compared to analyses where financial ratios and regression methods were employed as analytical review techniques. Results tentatively suggest that the ANN method recognized patterns within financial accounts more effectively than did financial ratio and regression methods. ANNs applied as a forecasting tool seem useful for identifying patterns that can indicate potential investigations of a firm's unaudited financial data in the current year.     

Corporate employment,red flags,and audit effort

U.S. regulatory agencies and congressional oversight committees have expressed concerns that auditors often neglect red flags embedded in the operating characteristics of firms that misstate their financial reports. This study examines whether labor employment decisions, a major part of a firm’s operations, help predict accounting improprieties and consequently play a role in audit planning and pricing. We find that negative abnormal employment changes are associated with a higher likelihood of subsequent financial restatements, accounting irregularities, and lawsuits related to accounting fraud, and generally require greater effort from auditors as manifested by higher audit fees and longer audit report lags. Positive abnormal employment changes are associated with subsequent restatements and longer audit report lags, but not associated with fraud or audit fees. Taken together, the results are consistent with auditors recognizing the individual misstatement risks pertaining to companies’ employment decisions. These results suggest that standard setters, regulators, and practitioners should devote more attention to operational statistics to identify potential red flags.     

Perceived importance of red flags across fraud types

The purpose of this study is to examine whether internal auditors, external auditors and economic crime investigators perceive the importance of red flags as significantly different across two fraud types: fraudulent financial reporting and misappropriation of assets, as well as across within-subject categories. A total of 471 useable responses were collected using a web-based survey. The findings indicate that significant differences exist on both single and aggregate mean levels among the participant groups. Internal auditors report a higher perceived importance of the red flags related to detecting misappropriation of assets than of those related to fraudulent financial reporting, whereas the opposite is true for economic crime investigators. For external auditors, only small differences in aggregate means between misappropriation of assets and fraudulent financial reporting were found. As the sensitivity to fraud type may affect professional planning, procedures and techniques with regard to fraud prevention, detection and investigation, the results may have both practical and theoretical implications. Further, the focus on both fraud types adds to prior literature on fraud.     

Improving Experienced Auditors’ Detection of Deception in CEO Narratives

We experimentally study the deception detection capabilities of experienced auditors, using CEO narratives from earnings conference calls as case materials. We randomly assign narratives of fraud and nonfraud companies to auditors as well as the presence versus absence of an instruction explaining that cognitive dissonance in speech is helpful for detecting deception. We predict this instruction will weaken auditors’ learned tendency to overlook fraud cues. We find that auditors’ deception judgments are less accurate for fraud companies than for nonfraud companies, unless they receive this instruction. We also find that instructed auditors more extensively describe red flags for fraud companies and more accurately identify specific sentences in narratives that pertain to underlying frauds. These findings indicate that instructing experienced auditors to be alert for cognitive dissonance in CEO narratives can activate deception detection capabilities.     

An Evaluation of the Corporate Takeover Model Using Neural Networks

Neural networks have been found to be promising in financial prediction tasks like bankruptcy and loan defaults. Their use in the capital markets is relatively new, although they have been used with some success in picking undervalued stocks. Accurate prediction of corporate takeover targets results in high financial payoffs. Researchers have used statistical procedures like logistic regression with little success in predicting corporate takeover targets. We use neural networks that are capable of producing complex mapping functions to predict mergers. We develop several neural network models carefully controlling for overfitting. Our results indicate that although neural networks map the data very well, they do not predict merger targets significantly better than logistic regression. This strongly suggests that the financial models used to predict mergers are inadequate. Firms should approach the development of merger prediction models cautiously and identify other factors that are more likely to predict mergers. Attempts to apply better analysis techniques to existing models will most likely produce similar results.     

Making trading decisions for financial‐engineered derivatives: a novel ensemble of neural networks using information content

Over the last decades, there has been a growing interest in applying artificial intelligence techniques to solve a spectrum of financial problems. A number of studies have shown promising results in using artificial neural networks (ANNs) to guide investment trading. Given the expanding role of ANNs in financial trading, this paper proposes the use of a hybrid neural network, which consists of two independent ANN architectures, and comparatively evaluates its performance against independent ANNs and econometric models in the trading of a financial‐engineered (synthetic) derivative composed of options on foreign exchange futures. We examine the financial profitability and the market timing ability of the competing neural network models and statistically compare their attributes with those based on linear and nonlinear statistical projections. A random walk model and the option pricing method are also included as benchmarks for comparison. Our empirical investigation finds that, for each of the currencies analysed, trading strategies guided by the proposed dual network are financially profitable and yield a more stable stream of investment returns than the other models. Statistical results strengthen the notion that diffusion of information contents and cross‐validation between the independent components within the dual network are able to reduce bias and extreme decision making over the long run. Moreover, the results are robust with respect to different levels of transaction costs. Copyright © 2009 John Wiley & Sons, Ltd.     

The Informational Role of Short Sellers: The Evidence from Short Sellers’ Reports on US‐Listed Chinese Firms

Using US‐listed Chinese firms as the setting, this paper studies a novel channel through which investors can acquire information about firms’ financial reporting quality, that is, the reports published voluntarily by short sellers. I find that short sellers tend to target firms that have financial reporting red flags and that exhibit ‘good’ operating performance and stock valuations. Targeted firms experience an average three‐day cumulative abnormal return (CAR) of ?6.4%, and ?13.6% for initial coverage of the firm, and the CARs are more negative when the reports allege more severe misconduct of the firms. Non‐targeted firms also experience losses in value following short seller reports, especially when they hire the same non‐Big 4 auditors as targeted firms and when their earnings quality is poor. In comparison, analysts fail to perform proper due diligence and are much less effective than short sellers in exposing misreporting risk in Chinese firms.     

Alternative perspectives to deal with auditors’ agency problem

Auditors’ agency problem stems from the mechanism according to which auditors (the agents) are being appointed to companies and paid for their services by the managements they audit (the principals). This mechanism creates an inherent conflict of interests for auditors. The Sarbanes-Oxley Act of 2002 was enacted as part of the efforts to strengthen auditors’ independence and mitigate the effect managements have on their auditors. However, the Act has been, and still is criticized for deficiencies embedded in its provisions. This paper presents an alternative regulatory framework for auditors based on analysis of the Sarbanes-Oxley Act provisions related to auditors and of other perspectives to deal with auditors’ agency problem from previous studies. The proposed framework aims to decrease the ability and incentives of both managements and auditors to collaborate in financial statement fraud. Under the premise that auditors need to function in a framework that discourages immoral behavior, the main provisions of the Sarbanes-Oxley Act related to auditors’ independence are addressed, requiring audit-firm rotation instead of audit-partner rotation, and expending the time-window between provision of audit and non-audit services. In addition, it is proposed that retiring audit firms accompany “entering” audit firms until completion of the first annual financial statement audit and that audit fees will be scrutinized by the SEC.     

Where were the auditors? Using AAERs in introductory or advanced auditing courses

I provide instructions for use of a Securities and Exchange Commission (SEC) Accounting and Auditing Enforcement Release (AAER) assignment by instructors in Introductory or Advanced Audit Courses. The assignment gives students an opportunity to use the knowledge they have gained from their auditing and other accounting courses. Students analyze what was done by individuals in a company to cause the SEC to issue an AAER and what the external auditors could have done to prevent the AAER from happening. A secondary feature of the assignment is that students are able to practice their presentation skills by presenting their analysis to their class members and instructor. The assignment can also lead to class discussion on ethics and what ethical dilemmas practicing auditors are faced with.     

Bankruptcy prediction of financially stressed firms: an examination of the predictive accuracy of artificial neural networks

This is an extension of prior studies that have used artificial neural networks to predict bankruptcy. The incremental contribution of this study is threefold. First, we use only financially stressed firms in our control sample. This enables the models to more closely approximate the actual decision processes of auditors and other interested parties. Second, we develop a more parsimonious model using qualitative ‘bad news’ variables that prior research indicates measure financial distress. Past research has focused on the ‘usefulness’ of accounting numbers and therefore often ignored non‐accounting variables that may contribute to the classification accuracy of the distress prediction models. In addition, rather than use multiple financial ratios, we include a single variable of financial distress using the Zmijewski distress score that incorporates ratios measuring profitability, liquidity, and solvency. Finally, we develop and test a genetic algorithm neural network model. We examine its predictive ability to that of a backpropagation neural network and a model using multiple discriminant analysis. The results indicate that the misclassification cost of the genetic algorithm‐based neural network was the lowest among the models. Copyright © 2001 John Wiley & Sons, Ltd.     

PREDICTING NEXT TRADING DAY CLOSING PRICE OF QATAR EXCHANGE INDEX USING TECHNICAL INDICATORS AND ARTIFICIAL NEURAL NETWORKS

Accurate prediction of stock market price is of great importance to many stakeholders. Artificial neural networks (ANNs) have shown robust capability in predicting stock price return, future stock price and the direction of stock market movement. The major aim of this study is to predict the next trading day closing price of the Qatar Exchange (QE) Index using historical data from 3 January 2010 to 31 December 2012. A multilayer perceptron ANN architecture was used as a prediction model with 10 market technical indicators as input variables. The experimental results indicate that ANNs are an effective modelling technique for predicting the QE Index with high accuracy, outperforming the well‐established autoregressive integrated moving average models. To the best of our knowledge, this is the first attempt to use ANNs to predict the QE Index, and its performance results are comparable to, and sometimes better than, many stock market predictions reported in the literature. The ANN model also revealed that the weighted and simple moving averages are the most important technical indicators in predicting the QE Index, and the accumulation/distribution oscillator is the least important such indicator. The analysis results also indicated that the ANNs are resilient to stock market volatility. Copyright © 2014 John Wiley & Sons, Ltd.     

Determinants of going concern opinions and audit fees for development stage enterprises

Startup entities have been the focus of much political and academic interest recently. Development stage enterprises (DSEs), as defined by SFAS 7, are startup entities for which some publicly available information exists. New accounting standards have removed the DSE designation and related extra reporting requirements, and placed more responsibility on owners and managers to assess the ability of entities to continue as a going concern. We examined information from financial statements and audit reports of companies previously reporting as DSEs to investigate what increases the likelihood of receiving a going concern modification in auditors' opinions (GCO) and what affects audit fees. Our overall analyses indicate that the asset size of DSEs, negative working capital, and prior-year going concern modifications consistently influence going concern modifications to auditors' opinions. Managers should clearly consider these conditions when making their assessment of their companies' future going concern status. Our results indicate that the size of the audit firm did not influence the going concern modification decision, but Big4 auditors charge significantly higher fees than other auditors. Thus, managers/owners of DSEs should weigh the benefits of having a Big4 firm audit on their financial statements against the higher fees charged by those firms.     

An inconsistency in SEC disclosure requirements? The case of the “insignificant” private target

Although the SEC's main charge is to ensure the disclosure of material information, it has not always consistently defined materiality. We show that acquisitions of privately-held targets classified as “insignificant” by the SEC appreciably affect market prices, and therefore are material by the SEC's definition. We find significant returns in transactions with targets as small as 2% – compared with the SEC's disclosure threshold of 20% – of the acquirer. Further, an average of 19 undisclosed private acquisitions per year exceed the median IPO value in the same year for our sample period. However, because the SEC deems these transactions insignificant, information like target financial statements remains undisclosed to the market. Disclosure rules regarding target financial statements thus create a regulatory disconnect, in which information that is material is nevertheless deemed “insignificant” and therefore not disclosed.     

A comparison of the relative costs of financial distress models: artificial neural networks,logit and multivariate discriminant analysis

This study uses two artificial neural networks (ANNs), categorical learning/instar ANNs and probabilistic (PNN) ANNs, suitable for classification and prediction type issues, and compares them to traditional multivariate discriminant analysis (MDA) and logit to examine financial distress one to three years prior to failure. The results indicate that traditional MDA and logit perform best with the lowest overall error rates. However, when the relative error costs are considered, the ANNs perform better than traditional logit or MDA. Also, as the time period moves farther away from the eventual failure date, ANNs perform more accurately and with lower relative error costs than logit or MDA. This supports the conclusion that for auditors and other evaluators interested in early warning techniques, categorical learning network and probabilistic ANNs would be useful. © 1997 John Wiley & Sons, Ltd.     

PRICING AND HEDGING SHORT STERLING OPTIONS USING NEURAL NETWORKS

This paper compares the performance of artificial neural networks (ANNs) with that of the modified Black model in both pricing and hedging short sterling options. Using high‐frequency data, standard and hybrid ANNs are trained to generate option prices. The hybrid ANN is significantly superior to both the modified Black model and the standard ANN in pricing call and put options. Hedge ratios for hedging short sterling options positions using short sterling futures are produced using the standard and hybrid ANN pricing models, the modified Black model, and also standard and hybrid ANNs trained directly on the hedge ratios. The performance of hedge ratios from ANNs directly trained on actual hedge ratios is significantly superior to those based on a pricing model, and to the modified Black model. Copyright © 2012 John Wiley & Sons, Ltd.     

Predicting sovereign debt crises using artificial neural networks: A comparative approach

Recent episodes of financial crisis have revived interest in developing models able to signal their occurrence in timely manner. The literature has developed both parametric and non-parametric models, the so-called Early Warning Systems, to predict these crises. Using data related to sovereign debt crises which occurred in developing countries from 1980 to 2004, this paper shows that further progress can be achieved by applying a less developed non-parametric method based on artificial neural networks (ANN). Thanks to the high flexibility of neural networks and their ability to approximate non-linear relationship, an ANN-based early warning system can, under certain conditions, outperform more consolidated methods.     

A neural network approach to the prediction of going concern status

The assessment of a firm's going concern status is not an easy task. To assist auditors, going concern prediction models based on statistical methods such as multiple discriminant analysis and logit/probit analysis have been explored with some success. This study attempts to look at a different and more recent approach—neural networks. In particular, a neural network model of the feedforward, backpropagation type was constructed to predict a firm's going concern status from six financial ratios, using a data set containing 165 non-going concerns and 165 matched going concerns. On an evenly distributed hold-out sample, the trained network model correctly predicted all 30 test cases. The results suggest that neural networks can be a promising avenue of research and application in the going concern area.     

A predictive system integrating intrinsic mode functions,artificial neural networks,and genetic algorithms for forecasting S&P500 intra‐day data

There is an abundant literature on the design of intelligent systems to forecast stock market indices. In general, the existing stock market price forecasting approaches can achieve good results. The goal of our study is to develop an effective intelligent predictive system to improve the forecasting accuracy. Therefore, our proposed predictive system integrates adaptive filtering, artificial neural networks (ANNs), and evolutionary optimization. Specifically, it is based on the empirical mode decomposition (EMD), which is a useful adaptive signal‐processing technique, and ANNs, which are powerful adaptive intelligent systems suitable for noisy data learning and prediction, such as stock market intra‐day data. Our system hybridizes intrinsic mode functions (IMFs) obtained from EMD and ANNs optimized by genetic algorithms (GAs) for the analysis and forecasting of S&P500 intra‐day price data. For comparison purposes, the performance of the EMD‐GA‐ANN presented is compared with that of a GA‐ANN trained with a wavelet transform's (WT's) resulting approximation and details coefficients, and a GA‐general regression neural network (GRNN) trained with price historical data. The mean absolute deviation, mean absolute error, and root‐mean‐squared errors show evidence of the superiority of EMD‐GA‐ANN over WT‐GA‐ANN and GA‐GRNN. In addition, it outperformed existing predictive systems tested on the same data set. Furthermore, our hybrid predictive system is relatively easy to implement and not highly time‐consuming to run. Furthermore, it was found that the Daubechies wavelet showed quite a higher prediction accuracy than the Haar wavelet. Moreover, prediction errors decrease with the level of decomposition.     

Predicting Corporate Failure Using Publicly Available Information

This study investigates the ability of publicly available failure-prediction models to predict the failure of companies listed on the Australian Stock Exchange. The failure-prediction models identified in the 1990 version ofAUP 17 were evaluated and re-estimated using recent Australian data. In addition, a model was developed incorporating publicly available information not previously included in Australian failure-prediction models. Variables measuring the size of the board of directors, changes to the board, the lag in reporting accounts, and average effective tax rates were added to the variable set. Most of the earlier models, the re-estimated models and the expanded model significantly outperformed chance, which suggests that auditors should consider using such models as part of their going-concern assessment procedures.     

SEC communications to the independent auditors: An analysis of enforcement actions

All 415 SEC releases issued between the end of 1972 and the end of 1989 were analyzed to clarify the SEC's philosophy of independent auditing and to document the violations of generally accepted auditing standards (GAAS) reported in the releases. Among the findings are 1) the SEC consistently concluded that the primary purpose of an independent audit is to enhance the efficiency of the capital markets and help protect the investing public by providing reasonable assurance concerning the integrity of the financial statements and related disclosures; 2) the SEC attributed many independent audit failures to questionable independent auditor judgement in adhering to professional standards, most often because of insufficient gathering of audit evidence due to over-reliance on management representations; 3) the large majority of cases in which the SEC associated the auditor with fraudulent financial reporting (usually constructive fraud) involved smaller audit firms; 4) the large majority of cases of management fraud in which the auditors were deceived by clients involved large audit firms. In the final section of this paper, we discuss the influence of enforcement releases on independent audit standard setting and possible implications for the audit profession in the future.